MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

com.trillboards/dooh

757,000+ screens reachable through Trillboards and 29,000+ screens registered on our own network. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: commerce-and-marketing · AI-classifiedversion 1.0.0streamable HTTP93 tools

Summary

com.trillboards/dooh is a remote MCP server listed in the official MCP registry at version 1.0.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 93 tools, 2 resources and 1 prompt.

Record checks

1 of 2 record checks met · 7 do not apply

met: Registry entry is active and says how to run it
not met: Source repository link opens
not applicable: Repository is not archived
not applicable: Code pushed to the repository in the 90 days before our check
not applicable: Repository publishes a security policy (SECURITY.md)
not applicable: Package names its licence with a standard (SPDX) identifier
not applicable: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
not applicable: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote (hosted by the publisher)
Transport: streamable HTTP
Sign-in: none needed to open a session
Tools: 93
Described as changing data: 31 of 93 toolsAI-classified
Mainly works on: accounts and data in outside web servicesAI-classified
Topic: commerce-and-marketingAI-classified
Last tested: 2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 11 tools whose name or declaration suggests they change data (create_creative_experiment, update_creative_policy, stop_creative_experiment, delete_device, create_webhook and 6 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

31 tools are described as changing something (import_feedback_creative, configure_feedback_brand, create_creative_experiment, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 1.0.0, published 2026-10-20 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-20 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.0 (published 2026-10-20).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

93tools

2resources

1prompts

What it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services.

31 of 93 tools are described as changing something (creating, editing, deleting, sending or running). For 13 the reading was uncertain, so no mark is shown.

import_feedback_creativecreates or changes datadescribed as changing data
“Import an AI model’s image through native bytes, moderation and brand review.”
Publisher declares: read-only no · destructive no · idempotent yes
Takes no inputs.
configure_feedback_brandcreates or changes datadescribed as changing data
“Configure your native brand profile and enable its booked reactive campaign.”
Publisher declares: read-only no · destructive no · idempotent no
7 inputs, 3 required
- experiment_idstringrequired“Native experiment ID returned by create_creative_experiment.”
- brand_namestringrequired“Advertiser brand name for the experiment’s native campaign.”
- brand_rulesobjectrequired“Native brand colours, typography, voice, products and required or prohibited elements.”
- brand_assetsarray“Native brand reference assets used by creative generation.”
- brand_intent_textstring or null“Optional brand intent supplied to the native creative generator.”
- stancestring“Native reactive relationship used to generate or stage this creative.”
- profile_idstring“Optional existing brand profile owned by this advertiser and advertisement.”
create_creative_experimentcreates or changes datadescribed as changing data
“Create an experiment on a funded native media-buy placement.”
Publisher declares: read-only no · destructive no · idempotent yes
6 inputs, 5 required
- namestringrequired“Name for this funded creative feedback experiment.”
- media_buy_idstringrequired“Your funded native AdCP media buy ID.”
- package_idstringrequired“Native package ID within that media buy.”
- objectivestringrequired“Measured objective: gaze share 0–1, gaze overlap milliseconds, or capped mean dwell milliseconds.”
- idempotency_keystringrequired“Caller-owned key for this exact operation; do not reuse for changed inputs.”
- expected_policy_versionstring“Exact decimal policy version; zero enrolls an unclaimed native policy.”
get_creative_experimentreads or searches
“Read your native experiment, policy and latest 500 owned creative recovery records.”
Publisher declares: read-only yes · destructive no · idempotent yes
1 input, 1 required
- experiment_idstringrequired“Native experiment ID returned by create_creative_experiment.”
register_creative_variantscreates or changes datadescribed as changing data
“Register approved native generated creative variants.”
Publisher declares: read-only no · destructive no · idempotent no
3 inputs, 3 required
- experiment_idstringrequired“Native experiment ID returned by create_creative_experiment.”
- expected_versionstringrequired“Exact decimal policy version from the latest experiment; stale updates return 409.”
- variantsarrayrequired“Approved native variants; identity and bytes remain immutable.”
update_creative_policycreates or changes datadescribed as changing data
“Replace native creative weights at the expected policy version.”
Publisher declares: read-only no · destructive no · idempotent no
3 inputs, 3 required
- experiment_idstringrequired“Native experiment ID returned by create_creative_experiment.”
- expected_versionstringrequired“Exact decimal policy version from the latest experiment; stale updates return 409.”
- weightsarrayrequired“Replacement weights for registered variants; omitted variants are inactive.”
get_creative_rewardsreads or searches
“Read a metered page of latest measured native play states.”
Publisher declares: read-only yes · destructive no · idempotent yes
6 inputs, 4 required
- experiment_idstringrequired“Native experiment ID returned by create_creative_experiment.”
- fromstringrequired“Inclusive first play date, YYYY-MM-DD; date range is at most 31 days.”
- torequired“Inclusive last play date, YYYY-MM-DD; date range is at most 31 days.”
- limitinteger“Maximum native play states returned on this metered page.”
- cursorstring“Opaque next_cursor from this same date scope; rewind after scan_complete.”
- idempotency_keystringrequired“Unique caller-owned billing key for this page; committed retries return the receipt, not another read.”
stop_creative_experimentdeletesdescribed as changing data
“Stop the native experiment at the expected policy version.”
Publisher declares: read-only no · destructive yes · idempotent no
2 inputs, 2 required
- experiment_idstringrequired“Native experiment ID returned by create_creative_experiment.”
- expected_versionstringrequired“Exact decimal policy version from the latest experiment; stale updates return 409.”
generate_brand_creativegenerates contentdescribed as changing data
“Generate a native brand creative for explicit review and moderation.”
Publisher declares: read-only no · destructive no · idempotent yes
5 inputs, 2 required
- experiment_idstringrequired“Native experiment ID returned by create_creative_experiment.”
- stancestring“Native reactive relationship used to generate or stage this creative.”
- aspectRatiostring“Image aspect ratio, such as 16:9, matched to your booked screens.”
- briefstring“Creative direction added to your configured native brand rules.”
- idempotency_keystringrequired“Unique caller-owned generation key; committed retries expose creativeId and renderKey in the receipt.”
review_feedback_creativecreates or changes datadescribed as changing data
“Approve or reject your generated creative using native brand review.”
Publisher declares: read-only no · destructive no · idempotent no
3 inputs, 3 required
- experiment_idstringrequired“Native experiment ID returned by create_creative_experiment.”
- creative_idstringrequired“Owned native creative ID awaiting your explicit brand review.”
- decisionstringrequired“Approve or reject brand use; global AI moderation remains a separate gate.”
register_partneron 1 other servercreates or changes datadescribed as changing data
“Register a new partner organization with Trillboards.”
7 inputs, 2 required
- company_namestringrequired“Company or organization name”
- emailstringrequired“Contact email for the partner account”
- websitestring“Company website URL (optional)”
- contact_namestring“Primary contact person name (optional)”
- contact_phonestring“Contact phone number (optional)”
- industrystring“Industry type (e.g., "vending", "retail", "hospitality")”
- expected_devicesinteger“Estimated number of devices to connect”
get_partner_infoon 3 other serversreads or searches
“Get information about the authenticated partner account.”
Takes no inputs.

Show 81 more tools

register_deviceon 1 other servercreates or changes datadescribed as changing data
“Register or update a device in the partner's network.”
6 inputs, 1 required
- device_idstringrequired“Your internal unique device identifier”
- namestring“Human-readable device name”
- device_typestring“Type of device”
- locationobject“Device location information”
- specsobject“Device specifications”
- metadataobject“Additional custom metadata”
list_deviceson 32 other serversreads or searches
“List all devices registered to the partner account.”
4 inputs
- statusstring“Filter by device status”
- device_typestring“Filter by device type”
- limitinteger“Maximum number of devices to return (default: 50, max: 100)”
- offsetinteger“Pagination offset”
get_deviceon 7 other serversreads or searches
“Get detailed information about a specific device.”
1 input, 1 required
- device_idstringrequired“Your internal device identifier”
delete_deviceon 2 other serversdeletesdescribed as changing data
“Soft-delete a device from the partner account.”
1 input, 1 required
- device_idstringrequired“Your internal device identifier to delete”
get_device_adsreads or searches
“Get current ads scheduled for a device (for testing).”
1 input, 1 required
- fingerprintstringrequired“Device fingerprint (e.g., "P_abc123")”
record_impressioncreates or changes datadescribed as changing data
“Record a single ad impression from a device.”
5 inputs, 2 required
- fingerprintstringrequired“Device fingerprint (e.g., "P_abc123")”
- ad_idstringrequired“Advertisement ID (MongoDB ObjectId)”
- duration_secondsnumber“How long the ad was displayed (seconds)”
- timestampstring“ISO 8601 timestamp when impression occurred (optional, defaults to now)”
- metadataobject“Additional impression metadata”
batch_impressionscreates or changes datadescribed as changing data
“Record multiple impressions in a single request (up to 100).”
1 input, 1 required
- impressionsarrayrequired“Array of impression objects (max 100)”
device_heartbeatcreates or changes datadescribed as changing data
“Send a heartbeat signal from a device to report its status.”
5 inputs, 1 required
- fingerprintstringrequired“Device fingerprint (e.g., "P_abc123")”
- statusstring“Current device status”
- current_ad_idstring“Currently playing ad ID (if status is "playing")”
- uptime_secondsinteger“Device uptime in seconds”
- error_messagestring“Error message (if status is "error")”
get_analyticson 32 other serversreads or searches
“Get analytics data for the partner account.”
4 inputs
- start_datestring“Start date in YYYY-MM-DD format (optional, defaults to 30 days ago)”
- end_datestring“End date in YYYY-MM-DD format (optional, defaults to today)”
- group_bystring“How to group the analytics data”
- device_idstring“Filter to a specific device (optional)”
create_webhookon 34 other serverscreates or changes datadescribed as changing data
“Create a new webhook subscription for real-time events.”
4 inputs, 2 required
- urlstringrequired“HTTPS endpoint URL to receive webhook events”
- eventsarrayrequired“Events to subscribe to”
- secretstring“HMAC signing secret for verifying webhook authenticity (optional but recommended)”
- descriptionstring“Human-readable description for this webhook”
list_webhookson 59 other serversreads or searches
“List all webhook subscriptions for the partner account.”
Takes no inputs.
update_webhookon 20 other serverscreates or changes datadescribed as changing data
“Update an existing webhook subscription.”
Takes no inputs.
delete_webhookon 49 other serversdeletesdescribed as changing data
“Delete a webhook subscription.”
1 input, 1 required
- webhook_idstringrequired“Webhook ID to delete (wh_xxx format or legacy ObjectId)”
test_webhookon 17 other serverssends messagesdescribed as changing data
“Send a test event to a webhook endpoint.”
2 inputs, 1 required
- webhook_idstringrequired“Webhook ID to test (wh_xxx format or legacy ObjectId)”
- eventstring“Event type to simulate (optional, defaults to device.online)”
get_webhook_deliverieson 1 other serverreads or searches
“Get delivery history for a webhook.”
3 inputs, 1 required
- webhook_idstringrequired“Webhook ID to get deliveries for (wh_xxx format or legacy ObjectId)”
- limitinteger“Maximum number of deliveries to return (default: 50, max: 100)”
- statusstring“Filter by delivery status”
discover_inventoryreads or searches
“Discover available DOOH screens across the exchange network.”
4 inputs
- venue_typesarray“Filter by venue types: transit, retail, outdoor, health_beauty, point_care, education, office, entertainment, government, financial, residential”
- locationobject“Location filter — use city/state OR lat/lng/radius_km”
- audience_profileobject“Filter screens by current audience characteristics”
- limitinteger“Maximum screens to return (default: 50, max: 200)”
get_live_audiencereads or searches
“Get real-time audience data for a specific screen.”
1 input, 1 required
- screen_idstringrequired“Screen ID to get live audience for”
get_audience_forecastreads or searches
“Predict what the audience will look like at a screen at a specific time.”
4 inputs, 3 required
- screen_idstringrequired“Screen ID to forecast”
- hourintegerrequired“Hour of day (0-23)”
- dayintegerrequired“Day of week (0=Sunday, 1=Monday, ..., 6=Saturday)”
- lookback_daysinteger“Days of historical data to use (default: 30)”
create_campaignon 22 other serverscreates or changes datadescribed as changing data
“Create a new advertising campaign targeting DOOH screens.”
12 inputs, 1 required
- namestringrequired“Campaign name”
- budget_cpmnumber“Bid CPM in USD (default: 4.0)”
- daily_budget_usdnumber“Daily budget cap in USD”
- total_budget_usdnumber“Total campaign budget in USD”
- screen_idsarray“Specific screen IDs to target (optional, overrides venue/geo targeting)”
- venue_typesarray“Venue types to target: transit, retail, outdoor, office, etc.”
- targetingobject“Additional targeting criteria”
- creative_urlstring“URL to video/image creative asset”
- creative_typestring“Creative format”
- creative_durationinteger“Duration in seconds (default: 15)”
- start_datestring“Campaign start date (ISO 8601)”
- end_datestring“Campaign end date (ISO 8601)”
get_campaign_performanceon 2 other serversreads or searches
“Get detailed performance metrics for a campaign.”
1 input, 1 required
- campaign_idstringrequired“Campaign UUID returned from create_campaign”
get_network_statson 12 other serversreads or searches
“Get network-wide statistics across all partner screens.”
1 input
- time_rangestring“Time range for stats (default: 7d)”
get_signalson 25 other serversreads or searches
“[AdCP Signals] Get real-time audience signals from DOOH screens.”
2 inputs
- paginationobject
- signal_specstring or object“Natural language description of the desired signals (AdCP form), or a structured Trillboards signal specification.”
activate_signalcreates or changes datadescribed as changing data
“[AdCP Signals] Activate an audience signal for DSP targeting.”
5 inputs, 2 required
- signal_agent_segment_idstring
- signal_typestringrequired“Type of signal to activate (e.g., "audience", "venue", "behavior")”
- parametersobjectrequired“Signal parameters to activate as targeting”
- screen_idsarray“Specific screens to activate on (optional, defaults to all partner screens)”
- destinationsarray“Where to push activated segments”
get_adcp_capabilitieson 1 other serverreads or searches
“[AdCP] Get the seller agent's AdCP capabilities and supported protocols.”
Takes no inputs.
get_productson 13 other serversreads or searches
“[AdCP Media Buy] Get available DOOH advertising products and packages.”
7 inputs
- buying_modestring“AdCP buying mode (default: brief)”
- briefstring“Natural language campaign brief for AI-driven inventory matching”
- filtersobject“Structured filters for wholesale/refine modes”
- marketstring“Market/city to get products for”
- venue_typesarray“Filter by venue types (legacy, prefer filters.venue_types)”
- audience_profileobject“Target audience characteristics”
- paginationobject
list_creativeson 4 other serversreads or searches
“[AdCP Creative] List the creatives this buyer has on file with us.”
15 inputs
- filtersobject“Narrow the result set.”
- sortobject
- paginationobject
- include_assignmentsboolean“Include which media buys each creative is attached to.”
- include_snapshotboolean
- include_itemsboolean
- include_variablesboolean
- include_pricingboolean
- include_purgedboolean
- include_webhook_activityboolean
- webhook_activity_limitinteger
- accountobject
- fieldsarray
- contextobject
- extobject
list_creative_formatsreads or searches
“[AdCP Media Buy] List the creative formats this network actually accepts.”
11 inputs
- format_idsarray“Return only these formats.”
- asset_typesarray“Filter to formats containing these asset types, e.g.”
- min_widthnumber“Minimum render width in pixels (inclusive)”
- max_widthnumber“Maximum render width in pixels (inclusive)”
- min_heightnumber“Minimum render height in pixels (inclusive)”
- max_heightnumber“Maximum render height in pixels (inclusive)”
- is_responsiveboolean“Filter for responsive formats.”
- name_searchstring“Case-insensitive partial match on the format name”
- publisher_domainstring“Resolve formats for this publisher.”
- paginationobject“Cursor-based pagination”
- contextobject
get_media_buysreads or searches
“[AdCP Media Buy] List media buys with status, budget, flight and optional delivery snapshots.”
5 inputs
- media_buy_idsarray“Specific media buy IDs.”
- status_filterstring or array“Single status or array of statuses.”
- include_snapshotboolean“Include a delivery snapshot per package (impressions, spend, pacing_index).”
- paginationobject
- contextobject
create_media_buyon 1 other servercreates or changes datadescribed as changing data
“[AdCP Media Buy] Create a media buy (campaign) from an AdCP buy specification.”
11 inputs
- namestring“Media buy name”
- packagesarray“AdCP product packages to buy”
- brandobject“Brand reference”
- total_budgetobject
- contextobject
- start_timestring“ISO 8601 start time”
- end_timestring“ISO 8601 end time”
- buy_specobject“Buy specification (legacy)”
- creativeobject
- buyer_refstring“External reference ID from the buyer/agency”
- idempotency_keystring
update_media_buycreates or changes datadescribed as changing data
“[AdCP Media Buy] Update an existing media buy (campaign).”
17 inputs, 1 required
- media_buy_idstringrequired“Media buy ID to update”
- packagesarray
- contextobject
- pausedboolean
- canceledboolean
- cancellation_reasonstring
- start_timestring
- end_timestring
- revisioninteger
- idempotency_keystring
- accountobject
- new_packagesarray
- invoice_recipientobject
- reporting_webhookobject
- push_notification_configobject
- extobject
- updatesobject“Fields to update”
sync_creativescreates or changes datadescribed as changing data
“[AdCP Media Buy] Validate and sync creative assets for a media buy.”
12 inputs, 1 required
- media_buy_idstring“Media buy ID”
- idempotency_keystring
- accountobject
- contextobject
- assignmentsarray
- delete_missingboolean
- dry_runboolean
- validation_modestring
- push_notification_configobject
- creative_idsarray
- extobject
- creativesarrayrequired“Creative assets to validate”
get_media_buy_deliveryon 1 other serverreads or searches
“[AdCP Media Buy] Get delivery/performance report for a media buy.”
3 inputs, 1 required
- media_buy_idstringrequired“Media buy ID”
- dimensionsarray“Reporting dimensions to include.”
- breakdown_byarray“Dimensions to break down by (legacy, prefer dimensions).”
provide_performance_feedbackon 1 other servercreates or changes datadescribed as changing data
“[AdCP Media Buy] Provide optimization signals from buyer agent.”
2 inputs, 2 required
- media_buy_idstringrequired“Media buy ID”
- feedbackobjectrequired“Performance feedback data”
log_eventon 3 other serverscreates or changes datadescribed as changing data
“[AdCP Media Buy] Record a conversion or attribution event.”
2 inputs, 2 required
- media_buy_idstringrequired“Media buy ID”
- eventobjectrequired“Event data”
list_accountson 42 other serversreads or searches
“[AdCP Accounts] List the accounts this credential can transact on.”
5 inputs
- accountobject“Exact account filter.”
- statusstring“Filter by account status.”
- sandboxboolean“Filter by sandbox status — matched against the account's real state, not a stub.”
- paginationobject
- contextobject
sync_accountscreates or changes datadescribed as changing data
“[AdCP Accounts] Establish or confirm the account behind this credential.”
6 inputs, 2 required
- idempotency_keystringrequired“Client-generated key for safe retries.”
- accountsarrayrequired“Per-account entries.”
- delete_missingboolean“Not supported — this seller never deletes an account from a sync.”
- dry_runboolean“Echo what would happen without applying it.”
- push_notification_configobject
- contextobject
get_task_statuson 13 other serversreads or searches
“[AdCP Protocol] Get the status of a previously issued AdCP task.”
5 inputs, 1 required
- task_idstringrequired“Unique identifier of the task to retrieve, as issued in the `task_id` field of the originating task response.”
- include_resultboolean“Include the task's result payload when status is completed.”
- include_historyboolean“Include conversation history.”
- accountobject
- contextobject
tasks_getreads or searches
“[AdCP Protocol] Get the status of a previously issued AdCP task.”
5 inputs, 1 required
- task_idstringrequired“Unique identifier of the task to retrieve, as issued in the `task_id` field of the originating task response.”
- include_resultboolean“Include the task's result payload when status is completed.”
- include_historyboolean“Include conversation history.”
- accountobject
- contextobject
list_taskson 66 other serversreads or searches
“[AdCP Protocol] List AdCP tasks belonging to your account, newest first.”
4 inputs
- filtersobject“Narrow the returned tasks.”
- paginationobject
- accountobject
- contextobject
tasks_liston 3 other serversreads or searches
“[AdCP Protocol] List AdCP tasks belonging to your account, newest first.”
4 inputs
- filtersobject“Narrow the returned tasks.”
- paginationobject
- accountobject
- contextobject
get_pricingon 192 other serversreads or searches
“Get machine-readable pricing for all Trillboards products.”
1 input
- productstring“Optional: filter to a specific product (data_api, proof_of_play, attribution, data_marketplace, partner_platform, programmatic, fein_edge_ai)”
get_usage_summaryon 5 other serversreads or searches
“Get your current billing period usage summary with per-product breakdown and costs.”
Takes no inputs.
setup_billingdescribed as changing data
“Set up pay-per-use billing with a Stripe payment method.”
1 input, 1 required
- payment_method_idstringrequired“Stripe payment method token (pm_xxx) from Stripe.js or Elements”
purchase_creditson 4 other serversmoves moneydescribed as changing data
“Purchase committed-use credits at a discount.”
2 inputs, 2 required
- tierstringrequired“Credit purchase tier”
- idempotency_keystringrequired“Stable logical purchase ID.”
get_billing_statuson 3 other serversreads or searches
“Check current billing status including whether billing is set up, credit balance, Stripe customer ID, and payment method status.”
Takes no inputs.
get_campaign_attributionreads or searches
“Get comprehensive attribution summary for a DOOH campaign.”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier (UUID or string ID from create_campaign)”
get_attribution_timeseriesreads or searches
“Get daily attribution timeseries for a campaign.”
3 inputs, 1 required
- campaign_idstringrequired“Campaign identifier”
- start_datestring“Start date (YYYY-MM-DD).”
- end_datestring“End date (YYYY-MM-DD).”
get_attention_metricsreads or searches
“Get edge AI attention metrics for a campaign (FEIN-powered).”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier”
get_creative_attentionreads or searches
“Get per-creative attention breakdown for a campaign.”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier”
get_multi_touch_attributionreads or searches
“Get multi-touch attribution model results for a campaign.”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier”
get_cross_channel_journeyreads or searches
“Get cross-channel customer journey data (Sankey flow) for a campaign.”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier”
get_incrementalityreads or searches
“Get incrementality/lift test results for a campaign.”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier”
create_experimenton 4 other serverscreates or changes datadescribed as changing data
“Create an incrementality experiment for a campaign.”
8 inputs, 2 required
- campaign_idstringrequired“Campaign identifier”
- experiment_typestringrequired“Experiment type: geo_holdout (matched DMAs), ghost_ads (PSA control), psm (propensity score matching)”
- treatment_dmasarray“DMA codes for treatment group (get ads)”
- control_dmasarray“DMA codes for control group (no ads)”
- holdout_pctnumber“Fraction of devices to hold out (0.05-0.50).”
- target_mdenumber“Minimum detectable effect (relative, e.g.”
- target_powernumber“Statistical power (0.80 or 0.90).”
- target_alphanumber“Significance level (0.05 or 0.01).”
get_creative_attributionreads or searches
“Get attribution performance by individual creative variant.”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier”
get_roasreads or searches
“Get Return on Ad Spend (ROAS) with transaction attribution data.”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier”
export_cohortcreates or changes datadescribed as changing data
“Export exposed audience cohort to a DSP for retargeting.”
2 inputs, 2 required
- campaign_idstringrequired“Campaign identifier”
- destinationstringrequired“DSP destination: ttd (The Trade Desk), dv360 (Google DV360), meta (Meta/Facebook), cadent, mediaocean”
get_audience_lookalikereads or searches
“Find screens with similar audience profiles using pgvector similarity.”
5 inputs, 1 required
- screen_idstringrequired“Source screen ID to find lookalikes for”
- limitinteger“Maximum number of results (default: 20, max: 100)”
- min_similaritynumber“Minimum cosine similarity threshold 0-1 (default: 0.7)”
- countrystring“Filter by country (optional)”
- venue_typestring“Filter by venue type (optional)”
semantic_audience_searchreads or searches
“Search screens by natural language scene description using pgvector.”
4 inputs, 1 required
- querystringrequired“Natural language description of the audience/scene to search for”
- limitinteger“Maximum number of results (default: 20, max: 100)”
- sincestring“Time window for scene data (e.g., "1h", "24h", "7d").”
- min_similaritynumber“Minimum semantic similarity threshold 0-1 (default: 0.5)”
get_campaign_heatmapreads or searches
“Get geographic exposure heatmap data for a campaign.”
1 input, 1 required
- campaign_idstringrequired“Campaign identifier”
verify_proof_of_playreads or searches
“Verify cryptographic proof of ad delivery or get campaign proofs.”
6 inputs
- campaign_idstring“Campaign ID to get proofs for (mutually exclusive with proof_payload)”
- proof_payloadobject“Proof data to verify (mutually exclusive with campaign_id).”
- start_datestring“Start date for proof query (YYYY-MM-DD, used with campaign_id)”
- end_datestring“End date for proof query (YYYY-MM-DD, used with campaign_id)”
- limitinteger“Max proofs to return (default: 1000, used with campaign_id)”
- cursorstring“Pagination cursor from previous response (used with campaign_id)”
query_observationson 1 other serverreads or searches
“Query the universal observation stream using natural language or structured filters.”
3 inputs, 1 required
- querystringrequired“Natural language query describing what observations to find”
- filtersobject“Structured filters to narrow results”
- limitinteger“Maximum observations to return (default: 100, max: 1000)”
semantic_search_observationsreads or searches
“Search observations by semantic similarity.”
3 inputs, 1 required
- querystringrequired“Natural language description of the observation moments to search for”
- filtersobject“Additional structured filters to narrow semantic search”
- limitinteger“Maximum results to return (default: 20, max: 100)”
anomaly_detecton 1 other serverreads or searches
“Detect anomalies in observation patterns.”
5 inputs, 1 required
- metricstringrequired“The metric to check for anomalies.”
- screen_idstring“Filter to a specific screen (mongo ID).”
- venue_typestring“Filter to a specific venue type.”
- lookback_hoursnumber“Hours of historical data to compute baseline from (default: 24, max: 168)”
- threshold_sigmanumber“Number of standard deviations to consider anomalous (default: 2.0, range: 1.0-5.0)”
cross_signal_correlatereads or searches
“Discover correlations between different signal types.”
3 inputs, 2 required
- signal_astringrequired“First signal to correlate (e.g., face_count, attention_score, crowd_energy, emotional_engagement, vehicle_count, noise_level, purchase_intent, ad_fill_rate)”
- signal_bstringrequired“Second signal to correlate against signal_a”
- filtersobject“Optional filters to narrow the correlation analysis”
configure_sensingcreates or changes datadescribed as changing data
“Configure what a screen should sense using natural language.”
3 inputs, 2 required
- screen_idstringrequired“Screen ID (mongo ID) to configure sensing for”
- intentstringrequired“Natural language description of what the screen should sense/detect/measure”
- auto_deployboolean“If true, automatically push the profile to the device.”
export_dataseton 9 other serversreads or searches
“Export observation data as a structured dataset.”
3 inputs, 2 required
- datasetstringrequired“Type of dataset to export”
- filtersobjectrequired“Filters to apply to the export”
- cursorstring“The previous page's metadata.next_cursor, to read the next page (same dataset and filters).”
predictive_queryreads or searches
“Generate predictive insights from observation patterns.”
4 inputs, 1 required
- questionstringrequired“Natural language question about the predicted trend or outcome”
- venue_typestring“Filter predictions to a specific venue type.”
- screen_idstring“Filter predictions to a specific screen (mongo ID).”
- time_horizonstring“How far ahead to predict (e.g., "1d", "3d", "7d", "14d").”
get_social_attentionreads or searches
“Query measured social attention events within your authorized screen and venue scope.”
5 inputs
- screen_idstring“Filter by screen MongoDB ID.”
- min_safnumber“Minimum social amplification factor threshold.”
- venue_typestring“Filter by venue type (e.g., "bar", "restaurant_qsr", "transit").”
- time_rangeobject“Time range filter.”
- limitinteger“Maximum results to return.”
find_similar_moments
“Find historically similar audience moments across the screen network using embedding similarity search.”
4 inputs, 1 required
- querystringrequired“Natural-language description of the target moment.”
- venue_typestring“Filter results to a specific venue type.”
- limitinteger“Maximum results to return.”
- min_similaritynumber“Minimum cosine similarity threshold (0-1).”
predict_moment_quality
“Predict the VAS (Viewability Attention Score) a specific creative would achieve at a given moment, based on historical data and causal modeling.”
2 inputs, 2 required
- moment_descriptionstringrequired“Natural-language description of the target moment context.”
- creative_idstringrequired“The creative/ad ID to predict performance for.”
recommend_creative
“Given a moment description, rank candidate creatives by predicted VAS performance.”
2 inputs, 2 required
- moment_descriptionstringrequired“Natural-language description of the target moment context.”
- creative_idsarrayrequired“Array of creative/ad IDs to rank.”
get_social_contagion_summary
“Aggregate social attention metrics across screens and time periods.”
2 inputs
- time_rangeobject“Time range filter.”
- group_bystring“Dimension to group by: "venue", "daypart", or "screen".”
get_dataset_statson 2 other servers
“Get statistics about available causal training data: total tuples, unique creatives, venue diversity, date range.”
Takes no inputs.
get_content_performance
“Get performance metrics for a video across the Trillboards DOOH network.”
3 inputs, 1 required
- video_idstringrequired“YouTube video ID to query performance for”
- daysinteger“Lookback window in days (default: 30, max: 90)”
- venue_typestring“Optional venue type filter (e.g., "retail", "transit", "bar")”
search_contenton 49 other servers
“Semantic search over content library using natural language queries and 768-D pgvector embeddings.”
3 inputs, 1 required
- querystringrequired“Natural language search query (min 3 characters)”
- limitinteger“Maximum results to return (default: 20, max: 100)”
- min_similaritynumber“Minimum cosine similarity threshold (default: 0.5, range: 0-1)”
get_content_recommendationson 1 other server
“Get best-performing content recommendations for a venue type and optional time context.”
3 inputs, 1 required
- venue_typestringrequired“Venue type to get recommendations for (required)”
- daypartstring“Optional daypart filter”
- limitinteger“Maximum recommendations to return (default: 10, max: 100)”
list_endpointson 28 other servers
“List every registered Trillboards API operation.”
3 inputs
- surfacestring“Filter to one surface (e.g.”
- agent_safeboolean“When true, return only endpoints flagged agent-safe.”
- idempotentboolean“When true, return only endpoints flagged idempotent.”
describe_endpointon 6 other servers
“Describe a single API operation including its parameters, response shape, and error codes.”
2 inputs, 2 required
- pathstringrequired“The operation path (OpenAPI template form, e.g.”
- methodstringrequired“HTTP method (case-insensitive).”
validate_request
“Validate a proposed request payload against the registered Zod schema for an operation, returning the exact canonical error envelope the HTTP surface would emit.”
3 inputs, 2 required
- pathstringrequired“Operation path (OpenAPI template form).”
- methodstringrequired
- payload“Shape is operation-dependent.”
list_error_codeson 1 other server
“List every error code in the Trillboards API error catalog.”
Takes no inputs.
query_changelog
“Query the Trillboards API changelog for recent changes, breaking changes, deprecations, and fixes.”
2 inputs
- sincestring“Only entries dated on or after this date (YYYY-MM-DD).”
- typestring“Filter by change category: "breaking", "additive", "deprecation", "fix".”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 80 tools
Says what it returns: 82% of 74 tools
States limits, defaults or errors: 6% of 78 tools
Says when to use it: 99% of 71 tools
Items covered per tool: 2.8 of 4 on average

Counted from the listing

Parameters with a description: 81% of 324
Tools with a description: 100% of 93
Typical description length: 762 characters

The tool set

Counted from the listing

Tools: 93
Size of the list: about 40,572 tokens for an agent to load (characters ÷ 4)
Naming: 93 of 93 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 80 of 93 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://api.trillboards.com/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "dooh": {
      "url": "https://api.trillboards.com/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "dooh": {
      "type": "http",
      "url": "https://api.trillboards.com/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"dooh","type":"http","url":"https://api.trillboards.com/mcp"}'

Claude Code

claude mcp add --transport http dooh https://api.trillboards.com/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://api.trillboards.com/mcp --transport http

Optional settings the entry also lists (left out above): Authorization.
The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint api.trillboards.com/mcp	Session opened	matches	our test · 2026-10-23
No credential declared as required	Opened a session without any credential	matches	our test · 2026-10-23

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: no public GitHub repository

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
Not metSource repository link opensThe registry entry gives no repository link.
Does not applyRepository is not archivedNo public GitHub repository to read.
Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about com.trillboards/dooh

Answered from the data above

Is com.trillboards/dooh safe to install?

We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 31 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does com.trillboards/dooh need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has com.trillboards/dooh been security tested?

Partly. 5 of the 16 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

What can com.trillboards/dooh do?

It lists 93 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete, send messages, move money and generate content. We did not call any tool, so this describes the text, not the behaviour.

Can com.trillboards/dooh change or delete data?

31 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

app.himalayas/mcpHimalayas Remote Jobsalso has tools that creates or changes data, deletes, generates content, moves money, reads or searches, sends messagescompare with this one
io.github.hermoso-ai/hermosoHermosoalso has tools that creates or changes data, deletes, generates content, moves money, reads or searches, sends messagescompare with this one
com.coordinalo/mcp-serverCoordinalo — Service Business Operationsalso has tools that creates or changes data, deletes, generates content, moves money, reads or searches, sends messagescompare with this one
io.github.bitsandtea/postking-mcpalso has tools that creates or changes data, deletes, generates content, moves money, reads or searches, sends messagescompare with this one
ai.mysiren/sirenSirenalso has tools that creates or changes data, deletes, generates content, moves money, reads or searches, sends messagescompare with this one
ai.oriiion/oriiionoriiionalso has tools that creates or changes data, deletes, generates content, moves money, reads or searches, sends messagescompare with this one

Active servers whose topic is also “commerce-and-marketing” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: exercised
Fake assistant turns: exercised
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: exercised

5 exercised11 not run (reason given)2 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 5 of the 16 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 5

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
12Hidden content
audience-hidingChecks resources that hide content from the user.exercised
13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 11

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside

Does not apply to this server · 2

14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted a read-only session with the server's remote endpoint
1,172 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 93 tools, 2 resources, 1 prompt.
5,783 msFinished: 5 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

commerce-and-marketing

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

The pages we read do not state how the product is priced.

Programming language

does not apply

no existing GitHub repository (server declares no repository link, so there is nothing to fetch)

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

prompts, resources, tools

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

does not apply

remote-only server: no package is shipped, so there is no package registry

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Integrity hash

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Signature / provenance

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Dependency advisories

does not apply

ships no package, so there are no dependencies to audit

Popularity

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Publisher signals

not stated

no readable GitHub owner to describe

Maintenance

does not apply

server declares no repository link, so there is nothing to fetch

Environment

the publisher's infrastructure

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “com.trillboards/dooh: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/com.trillboards/dooh

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/com.trillboards/dooh)](https://protocolprobe.com/mcp/servers/com.trillboards/dooh)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology