MCP servers › io.github.adwarp-dev › adwarp

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

io.github.adwarp-dev/adwarp

Open-source ad agent for LinkedIn Ads and Google Ads. Drafts campaigns, audiences and reports. — the publisher's description

8 of 9 record checks metRead-only · tools listed 2026-10-23Topic: commerce-and-marketing · AI-classifiedPricing: open-source · AI-classifiedversion 0.4.0TypeScriptMITstandard input/output, streamable HTTP37 tools

Summary

io.github.adwarp-dev/adwarp is a remote and local MCP server listed in the official MCP registry at version 0.4.0. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 37 tools, 0 resources and 0 prompts.

Record checks

8 of 9 record checks met

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met: The version the registry lists can be installed and is not withdrawn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

#4,648 of 15,112 packages by monthly downloads, tied with 6 others
#1,732 of 22,952 repositories by GitHub stars, tied with 28 others

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

Key facts

Runs: remote and local package
Transport: standard input/output, streamable HTTP
Package: npm · listed version current
License: MIT
Dependencies: no known high or critical advisories
Repository: public
Tools: 37
Described as changing data: 13 of 37 toolsAI-classified
Mainly works on: accounts and data in outside web servicesAI-classified
Topic: commerce-and-marketingAI-classified
Pricing: open-sourceAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

13 tools are described as changing something (gads_launch_search_campaign, upload_audience_csv, audience_from_salesforce, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
Its package is signed and carries a build record naming its source.

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

0.4.0, published 2026-10-19 (registry, as of the 2026-10-23 snapshot)

First listed version

2026-10-18 (earliest version still in the registry; older removed versions would be earlier)

Version history

3 versions listed, 2026-10-18 to 2026-10-19; 3 in the 90 days before the 2026-10-23 snapshot.

Most recent 3 versions

0.4.0 · 2026-10-19
0.3.0 · 2026-10-18
0.2.0 · 2026-10-18

(versions still listed in the registry only)

Registry data

snapshot 2026-10-23

Package and repository

checked 2026-10-23

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 0.4.0 (published 2026-10-19).

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

37tools

0resources

0prompts

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

13 of 37 tools are described as changing something (creating, editing, deleting, sending or running). For 1 the reading was uncertain, so no mark is shown.

gads_list_accountsreads or searches
“List every Google Ads customer this login can reach.”
Takes no inputs.
gads_list_client_accountsreads or searches
“List the client accounts under a Google Ads manager (MCC) account.”
1 input, 1 required
- managerIdstringrequired“Manager customer id, digits only”
gads_keyword_ideasreads or searches
“Keyword research: search volume, competition, and top-of-page bid range for seed terms and/or a landing page.”
6 inputs, 1 required
- customerIdstring
- seedsarrayrequired“Seed keywords or phrases”
- pageUrlstring
- locationsarray
- languagesarray
- limitinteger
gads_list_campaignsreads or searches
“Account structure: campaigns with their ad groups nested.”
2 inputs
- customerIdstring
- includeRemovedboolean
gads_list_adsreads or searches
“Ads in an ad group, with their responsive-search headlines and descriptions.”
2 inputs, 1 required
- customerIdstring
- adGroupIdstringrequired
gads_list_conversion_actionsreads or searches
“Conversion actions on the account, so a launch can name one instead of guessing an id.”
1 input
- customerIdstring
gads_launch_search_campaigndescribed as changing data
“Create a PAUSED Search campaign from a brief: budget, campaign, geo/language targeting, ad groups, keywords, and responsive search ads, all in one atomic mutate.”
15 inputs, 4 required
- customerIdstring“10-digit customer id; falls back to config default”
- campaignNamestringrequired
- dailyBudgetnumberrequired“Amount in the ad account's currency, e.g.”
- budgetNamestring“Defaults to the campaign name”
- cpcBid“Amount in the ad account's currency, e.g.”
- finalUrlstringrequired“Landing page for ads that do not override it”
- locationsarray“ISO country codes (US, GB) or raw geoTargetConstant ids”
- languagesarray“ISO language codes”
- adGroupsarrayrequired
- negativeKeywordsarray
- negativeKeywordListIdstring
- conversionActionNamesarray“Conversion actions to set as this campaign's goals; falls back to the config default”
- startDateTimestring
- endDateTimestring
- validateOnlyboolean
gads_performanceon 1 other serverreads or searches
“Performance rows at campaign, ad_group, ad, keyword, or search_term level, with totals and derived KPIs (CTR, CPC, CPM, conversion rate, cost per conversion).”
6 inputs
- customerIdstring
- levelstring
- periodstring
- startDatestring“YYYY-MM-DD”
- endDatestring“YYYY-MM-DD”
- campaignIdstring
gads_searchruns code or commands
“Run a raw GAQL query against the account.”
2 inputs, 1 required
- customerIdstring
- querystringrequired“A GAQL query.”
list_ad_accountson 1 other serverreads or searches
“List LinkedIn ad accounts this app can access.”
Takes no inputs.
list_targeting_facetsreads or searches
“List LinkedIn targeting facets you can target on.”
Takes no inputs.
search_targetingreads or searches
“Typeahead-search entities within a facet to get their URNs (e.g.”
2 inputs, 2 required
- facetstringrequired“short facet name, e.g.”
- querystringrequired

Show 25 more tools

list_facet_entitiesreads or searches
“List all entities of a small facet (e.g.”
1 input, 1 required
- facetstringrequired“short facet name, e.g.”
estimate_audienceon 1 other serverreads or searches
“Estimate audience size for a structured targeting spec (facet short name -> entity URNs).”
2 inputs, 1 required
- includeobjectrequired“facet short name -> entity URNs (ANDed across facets)”
- excludeobject“facet short name -> entity URNs to exclude”
upload_audience_csvcreates or changes datadescribed as changing data
“Clean a CSV at csvPath and upload it as a matched-audience DMP segment.”
4 inputs, 2 required
- accountIdstring
- namestringrequired
- csvPathstringrequired“Path to the CSV file on the server”
- typestring“Force the list type; auto-detected if omitted”
audience_from_salesforcecreates or changes datadescribed as changing data
“Build a matched audience from a Salesforce SOQL query that selects an email column.”
4 inputs, 3 required
- accountIdstringrequired
- namestringrequired“Audience/segment name”
- soqlstringrequired“SOQL selecting an email column, e.g.”
- emailFieldstring“Email column name if not 'Email'”
audience_from_hubspotcreates or changes datadescribed as changing data
“Build a matched audience from HubSpot contacts or companies.”
6 inputs, 1 required
- accountIdstring“LinkedIn ad account id; defaults to config defaultAccountId”
- namestringrequired“Audience/segment name”
- typestring“contact or company.”
- listIdstring“HubSpot list id (the ILS list id).”
- filtersarray“CRM search filters, all ANDed (HubSpot allows up to 6 per group).”
- dryRunboolean“Return counts and a masked sample without uploading anything”
list_conversionson 8 other serversreads or searches
“List the account's existing conversions (insight tags) so you can select one to track on a campaign.”
1 input
- accountIdstring
list_campaignson 34 other serversreads or searches
“List the account structure: campaign groups (campaigns) and/or their campaigns (ad groups), DRAFTS INCLUDED, unlike performance reports, which only show entities with spend.”
4 inputs
- accountIdstring
- levelstring
- groupIdstring“Scope campaigns to one campaign group id”
- includeArchivedboolean
list_adson 2 other serversreads or searches
“List the creatives (ads) in a campaign (ad group), drafts included: id, name, status, and backing post urn.”
2 inputs, 1 required
- accountIdstring
- campaignIdstringrequired
delete_addeletesdescribed as changing data
“Delete an ad: removes the creative and (best-effort) the Direct Sponsored Content post behind it.”
2 inputs, 1 required
- accountIdstring
- creativeIdstringrequired
update_adcreates or changes datadescribed as changing data
“Change a single ad's (creative's) status in place: PAUSED stops it serving, ACTIVE starts it serving, ARCHIVED retires it.”
4 inputs, 2 required
- accountIdstring“Numeric ad account id; defaults to the configured account”
- creativeIdstringrequired“Numeric creative (ad) id or a full urn:li:sponsoredCreative URN”
- statusstringrequired“PAUSED stops the ad serving.”
- dryRunboolean“Return the patch without sending it”
get_audience_statusreads or searches
“Check a DMP segment's matching status and resolved size.”
1 input, 1 required
- segmentIdstringrequired
create_campaign_groupcreates or changes datadescribed as changing data
“Create a campaign group (the top-level 'campaign').”
5 inputs, 2 required
- accountIdstringrequired“Numeric ad account id (no urn prefix)”
- namestringrequired
- statusstring
- totalBudgetobject
- runScheduleobject
create_campaignon 22 other serverscreates or changes datadescribed as changing data
“Create a campaign (the 'ad group') with targeting, budget, bid or bidding strategy (optimizationTargetType MAX_CLICK = Maximum Delivery on landing page clicks), schedule, and optional ad rotation (cr…”
22 inputs, 4 required
- accountIdstringrequired
- campaignGroupIdstringrequired“Numeric campaign group id”
- namestringrequired
- typestring
- objectiveTypestring“Campaign objective.”
- costTypestring
- dailyBudgetobject
- totalBudget
- unitCost“Bid amount”
- optimizationTargetTypestring“Bidding strategy.”
- localeobject
- runScheduleobjectrequired
- statusstring
- creativeSelectionstring“Ad rotation: OPTIMIZED (LinkedIn default, favors the predicted winner) or ROUND_ROBIN (rotate ads evenly)”
- targetingCriteriaobject
- targetingobject
- audienceSegmentUrnstring“urn:li:adSegment:...”
- geoUrnsarray“urn:li:geo:...”
- politicalIntentstring
- conversionIdsarray
- applyDefaultExclusionsboolean
- applyDefaultConversionboolean
update_campaignon 15 other serverscreates or changes datadescribed as changing data
“Update an existing campaign (the 'ad group') in place: change its targeting and/or name, status, budget, bid, bidding strategy (optimizationTargetType, costType), schedule, ad rotation (creativeSelec…”
17 inputs, 2 required
- accountIdstringrequired
- campaignIdstringrequired“Numeric campaign (ad group) id to update”
- targetingCriteriaobject
- targetingobject
- audienceSegmentUrnstring“urn:li:adSegment:...”
- geoUrnsarray“urn:li:geo:...”
- applyDefaultExclusionsboolean
- namestring
- statusstring
- dailyBudgetobject
- totalBudget
- costTypestring“Change the cost type (CPM for Maximum Delivery)”
- unitCost“Bid amount”
- optimizationTargetTypestring“Bidding strategy.”
- runScheduleobject
- creativeSelectionstring“Ad rotation: OPTIMIZED (favors the predicted winner) or ROUND_ROBIN (rotate ads evenly)”
- dryRunboolean
create_text_adon 1 other servercreates or changes datadescribed as changing data
“Create a Text Ad creative (DRAFT by default).”
6 inputs, 5 required
- accountIdstringrequired
- campaignIdstringrequired
- titlestringrequired
- textstringrequired
- clickUristringrequired
- statusstring
create_image_adcreates or changes datadescribed as changing data
“Create a single-image Sponsored Content creative (DRAFT).”
10 inputs, 6 required
- accountIdstringrequired
- campaignIdstringrequired
- organizationUrnstringrequired“urn:li:organization:...”
- commentarystringrequired“The post body / ad intro text”
- clickUristringrequired
- headlinestringrequired
- callToActionstring“Call-to-action button label”
- imagePathstring
- namestring“Ad name shown in Campaign Manager”
- statusstring
performance_summaryreads or searches
“Account performance rollup over a period: totals + KPIs, top campaigns by spend/CTR, worst by cost-per-conversion, and flagged campaigns (spend with no conversions, high CPC, low CTR).”
4 inputs
- accountIdstring
- periodstring
- startDatestring“YYYY-MM-DD; with endDate, overrides period”
- endDatestring“YYYY-MM-DD”
get_performanceon 11 other serversreads or searches
“Per-entity performance with derived KPIs (CTR, CPC, CPM, CPL, conversion rate).”
6 inputs
- accountIdstring
- levelstring“campaign_group=campaign, campaign=ad group, creative=ad”
- parentIdstring“Parent group id (for level=campaign) or campaign id (for level=creative)”
- periodstring
- startDatestring“YYYY-MM-DD; with endDate, overrides period”
- endDatestring“YYYY-MM-DD”
performance_trendreads or searches
“Weekly or monthly trend for one entity, with period-over-period deltas on impressions, clicks, spend, conversions, and CTR.”
6 inputs, 1 required
- levelstring
- entityIdstringrequired“Numeric id of the account/group/campaign/creative to trend”
- bucketstring
- periodstring
- startDatestring“YYYY-MM-DD; with endDate, overrides period”
- endDatestring“YYYY-MM-DD”
launch_from_briefdescribed as changing data
“End-to-end: optional audience upload -> campaign group -> campaign -> draft creatives.”
14 inputs, 5 required
- accountIdstringrequired
- campaignGroupNamestringrequired
- campaignNamestringrequired
- audienceobject
- dailyBudgetobjectrequired
- bid
- typestring
- runScheduleobjectrequired
- geoUrnsarray“Defaults to United States”
- targetingobject
- conversionIdsarray
- conversionNamestring“e.g.”
- creativeSelectionstring
- creativesarray
log_ad_changecreates or changes datadescribed as changing data
“Record a change to an ad entity in the local change journal, so a later lift report can compare performance before vs.”
10 inputs, 2 required
- entityTypestringrequired“campaignGroup (the 'campaign'), campaign (the 'ad group'), or creative (the 'ad')”
- entityIdstringrequired“Numeric id of the campaign group / campaign / creative”
- namestring“Human name of the entity (for nicer listings)”
- fieldstring“Field that changed, e.g.”
- beforestring“Prior value, if known”
- afterstring“New value”
- notestring“Freeform note (used when there is no specific field)”
- labelstring“Hypothesis/label, e.g.”
- tagsarray
- atstring“ISO 8601 time the change took effect; defaults to now”
list_ad_changesreads or searches
“List recorded ad changes (newest first) from the local change journal.”
4 inputs
- entityTypestring“campaignGroup (the 'campaign'), campaign (the 'ad group'), or creative (the 'ad')”
- entityIdstring
- tagstring
- limitinteger“Max rows (default 50)”
compute_liftcalculates or converts
“For each recorded change to an entity, compare performance in the window before the change against the window after it (default 14 days each side).”
3 inputs, 2 required
- entityTypestringrequired“campaignGroup (the 'campaign'), campaign (the 'ad group'), or creative (the 'ad')”
- entityIdstringrequired
- windowDaysinteger“Days on each side of a change (default 14)”
inspect_competitor_adsreads or searches
“Discover competitor ads through the official API.”
9 inputs
- advertiserstring“Competitor/advertiser display name (accountOwner)”
- companyIdstring“Numeric LinkedIn company id, more precise than name”
- keywordstring“Free-text keyword search across ad copy”
- countriesarray“ISO-3166 country codes to scope, e.g.”
- maxinteger“Max ads to collect”
- enginestring“auto = official API plus remote creative worker; api = metadata only.”
- deepboolean“Enqueue up to 10 verified company ads on the remote worker; reuse cached creatives.”
- concurrencynumber“Remote worker concurrency is fixed at one.”
- copyMaxinteger“Creative sample size, capped at 10.”
get_competitor_creativesreads or searches
“Read remote creative job status and cached copy by ad IDs.”
1 input, 1 required
- idsarrayrequired

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. 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 37 tools
Says what it returns: 94% of 35 tools
States limits, defaults or errors: 0% of 37 tools
Says when to use it: 19% of 37 tools
Items covered per tool: 2.1 of 4 on average

Counted from the listing

Parameters with a description: 46% of 185
Tools with a description: 100% of 37
Typical description length: 230 characters

The tool set

Counted from the listing

Tools: 37
Size of the list: about 9,683 tokens for an agent to load (characters ÷ 4)
Naming: 37 of 37 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 37 of 37 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. 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 npm package adwarp

Our sandbox started this package 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. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "adwarp": {
      "command": "npx",
      "args": [
        "-y",
        "adwarp@0.4.0",
        "mcp"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "adwarp": {
      "command": "npx",
      "args": [
        "-y",
        "adwarp@0.4.0",
        "mcp"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "adwarp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "adwarp@0.4.0",
        "mcp"
      ]
    }
  }
}

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

code --add-mcp '{"name":"adwarp","type":"stdio","command":"npx","args":["-y","adwarp@0.4.0","mcp"]}'

Claude Code

claude mcp add --transport stdio adwarp -- npx -y adwarp@0.4.0 mcp

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

npx @modelcontextprotocol/inspector@2.11.0 -- npx -y adwarp@0.4.0 mcp

Arguments are written as the registry entry gives them; a named one as “--name value”, the form the registry documentation shows.
Optional settings the entry also lists (left out above): ADWARP_LINKEDIN_CLIENT_ID, ADWARP_LINKEDIN_CLIENT_SECRET, ADWARP_LINKEDIN_REFRESH_TOKEN, ADWARP_LINKEDIN_DEFAULT_ACCOUNT_ID.
This runs the publisher's code on your machine (npx). Read its README first.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

From the remote endpoint (Streamable HTTP)

This entry needs values of your own (marked < > or { } in the config below), so there is no one-click link: paste the config and fill them in.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://mcp.adwarp.dev/api/mcp

The entry also requires the headers X-Adwarp-Linkedin-Client-Id, X-Adwarp-Linkedin-Client-Secret, X-Adwarp-Linkedin-Refresh-Token.

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

{
  "mcpServers": {
    "adwarp": {
      "url": "https://mcp.adwarp.dev/api/mcp",
      "headers": {
        "X-Adwarp-Linkedin-Client-Id": "<X-Adwarp-Linkedin-Client-Id>",
        "X-Adwarp-Linkedin-Client-Secret": "<X-Adwarp-Linkedin-Client-Secret>",
        "X-Adwarp-Linkedin-Refresh-Token": "<X-Adwarp-Linkedin-Refresh-Token>"
      }
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "adwarp": {
      "type": "http",
      "url": "https://mcp.adwarp.dev/api/mcp",
      "headers": {
        "X-Adwarp-Linkedin-Client-Id": "${input:x-adwarp-linkedin-client-id}",
        "X-Adwarp-Linkedin-Client-Secret": "${input:x-adwarp-linkedin-client-secret}",
        "X-Adwarp-Linkedin-Refresh-Token": "${input:x-adwarp-linkedin-refresh-token}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "x-adwarp-linkedin-client-id",
      "description": "X-Adwarp-Linkedin-Client-Id",
      "password": false
    },
    {
      "type": "promptString",
      "id": "x-adwarp-linkedin-client-secret",
      "description": "X-Adwarp-Linkedin-Client-Secret",
      "password": true
    },
    {
      "type": "promptString",
      "id": "x-adwarp-linkedin-refresh-token",
      "description": "X-Adwarp-Linkedin-Refresh-Token",
      "password": true
    }
  ]
}

Claude Code

claude mcp add --transport http adwarp https://mcp.adwarp.dev/api/mcp --header "X-Adwarp-Linkedin-Client-Id: <X-Adwarp-Linkedin-Client-Id>" --header "X-Adwarp-Linkedin-Client-Secret: <X-Adwarp-Linkedin-Client-Secret>" --header "X-Adwarp-Linkedin-Refresh-Token: <X-Adwarp-Linkedin-Refresh-Token>"

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://mcp.adwarp.dev/api/mcp --transport http

Replace <X-Adwarp-Linkedin-Client-Id>, <X-Adwarp-Linkedin-Client-Secret>, <X-Adwarp-Linkedin-Refresh-Token> with your own header values; the entry marks X-Adwarp-Linkedin-Client-Secret, X-Adwarp-Linkedin-Refresh-Token as secret, so keep the file out of version control.
Optional settings the entry also lists (left out above): X-Adwarp-Linkedin-Account-Id, X-Adwarp-Linkedin-Version.
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. The command above does not send the required headers (X-Adwarp-Linkedin-Client-Id, X-Adwarp-Linkedin-Client-Secret, X-Adwarp-Linkedin-Refresh-Token).

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.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 0.4.0
Latest stable: 0.4.0
Status: current
Withdrawn: no

Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-DqFQg+YIj+W1usuHH…
Signature: signed and attested
License: MIT

Source: the package registry · 2026-10-23.

Usage

Downloads: 596 in the last month

Source: api.npmjs.org · 2026-10-23.

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
Published package can be started	Started and answered	matches	our test · 2026-10-23
Version 0.4.0 on npm	Exists and can be installed	matches	npm · 2026-10-23
Repository github.com/adwarp-dev/adwarp	Opens publicly	matches	api.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: io.github.adwarp-dev
GitHub owner: an organization (adwarp-dev)
Build record: signed and attested

Repository: github.com/adwarp-dev/adwarp
Stars: 23
Repository age: 91–180 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

8 of 9 record checks met

#4,648 of 15,112 packages by monthly downloads, tied with 6 others
#1,732 of 22,952 repositories by GitHub stars, tied with 28 others

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
MetPackage names its licence with a standard (SPDX) identifierMIT
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Metnpm package carries build provenance (attestation)Signed, with a build attestation naming the source and workflow.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. 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 io.github.adwarp-dev/adwarp

Answered from the data above

Is io.github.adwarp-dev/adwarp safe to install?

We do not rate servers as safe or unsafe. 8 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its npm package carries a build-provenance attestation that names its source repository and build workflow. Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has advisories (2 moderate; npm audit). 13 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.

Is io.github.adwarp-dev/adwarp free to use?

Its website (adwarp.dev/) describes a open-source pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.

Has io.github.adwarp-dev/adwarp been security tested?

Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can io.github.adwarp-dev/adwarp do?

It lists 37 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, run code or commands and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.adwarp-dev/adwarp change or delete data?

13 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.

Does io.github.adwarp-dev/adwarp publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 0.4.0, the latest stable release on npm.

Where is the source code of io.github.adwarp-dev/adwarp?

In github.com/adwarp-dev/adwarp, which opens publicly.

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

io.github.hermoso-ai/hermosoHermosoalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.bitsandtea/postking-mcpalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.leanrads/leanriqLeanrIQalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
com.getadloop/adloopAdLoopalso has tools that creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
com.mcparmory/klaviyoalso has tools that calculates or converts, creates or changes data, deletes, reads or searchescompare with this one
com.mcparmory/shopify-adminalso has tools that calculates or converts, creates or changes data, deletes, reads or searchescompare 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

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. 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: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not applicable
Consent handling: not applicable
Sign-in metadata: not applicable

2 exercised10 not run (reason given)6 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 10

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against

Does not apply to this server · 6

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

Source: our own test in an isolated sandbox, 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 the published package in an isolated sandbox (read-only mode)
4,404 msConnected after 0 redirects.
Read the inventory: 37 tools, 0 resources, 0 prompts.
5,344 msFinished: 2 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

open-source

read from adwarp.dev/ · 2026-10-23

“Open-source ad agent for LinkedIn and Google Ads Adwarp”

Programming language

TypeScript

api.github.com · 2026-10-23

Hosting type

remote and local package

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

standard input/output, streamable HTTP

registry · 2026-10-23

Required credentials

requires a secret

registry · no declaration is not a guarantee

Package registry

npm

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-23

Integrity hash

declared (sri)

package registry · 2026-10-23

Signature / provenance

signed and attested

package registry · 2026-10-23

Dependency advisories

moderate

npm audit · 2026-10-23

Popularity

596 downloads a month

package registry · 2026-10-23

Publisher signals

owner: an organization · repository age: 91–180 days · stars: 10–99 · build record: signed and attested

api.github.com · 2026-10-23

Maintenance

active

api.github.com · 2026-10-23

Environment

either (remote or your machine)

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. “io.github.adwarp-dev/adwarp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.adwarp-dev/adwarp

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/io.github.adwarp-dev/adwarp)](https://protocolprobe.com/mcp/servers/io.github.adwarp-dev/adwarp)

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