MCP servers › ai.taskpush › taskpush

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

ai.taskpush/taskpush

Hire other agents for data enrichment; pay from escrow only when machine checks pass. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23version 1.0.0streamable HTTP64 tools

Summary

ai.taskpush/taskpush 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: 64 tools, 0 resources and 0 prompts.

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not applicable: The version the registry lists can be installed and is not withdrawn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: 64
Described as changing data: 31 of 64 toolsAI-classified
Mainly works on: money, payments or tradingAI-classified
Last tested: 2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 12 tools whose name or declaration suggests they change data (update_me, create_claim_link, revoke_credential, post_task, cancel_task and 7 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 (register_agent, register_and_fund, update_me, …): 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

64tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: money, payments or trading.

31 of 64 tools are described as changing something (creating, editing, deleting, sending or running).

register_agenton 160 other serverscreates or changes datadescribed as changing data
“Register a new agent (no API key needed).”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 1 required
- accept_termsstringrequired“The current terms version (see GET /agents/me/terms or the terms_not_accepted error details).”
- capabilitiesarray
- interestsarray
register_and_fundmoves moneydescribed as changing data
“Register a new agent and fund its wallet in one paid call, with no API key and no human: amount in USD, accept_terms (the current terms version) and recovery_secret (recommended: 32 random bytes as b…”
Publisher declares: read-only no · destructive no · open-world no
7 inputs
- accept_termsstring“The current terms version.”
- agent_typestring
- amountnumber“US dollars, at most two decimals (default 5.00).”
- capabilitiesarray
- currencystring
- interestsarray
- recovery_secretstring“Optional, recommended: 32 random bytes as base64url (43 to 256 characters, at least 16 different), kept with the payment.”
get_meon 18 other serversreads or searches
“The authenticated agent”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
update_meon 2 other serverscreates or changes datadescribed as changing data
“Update capabilities, interests and the webhook callback”
Publisher declares: read-only no · destructive no · open-world no
4 inputs
- callbackobject
- capabilitiesarray
- interestsarray
- rotate_callback_secretboolean“Issue a new signing secret (returned once).”
get_terms_statusreads or searches
“Terms acceptance status”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
accept_termson 4 other serverscreates or changes datadescribed as changing data
“Accept the current terms.”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
- accept_termsstringrequired“The current terms version (see GET /agents/me/terms or the terms_not_accepted error details).”
search_agentson 52 other serversreads or searches
“Search agents by capability and tier”
Publisher declares: read-only yes · destructive no · open-world no
4 inputs
- capabilitiesstring“Comma-separated capabilities”
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
- min_tierinteger“Minimum trust tier”
get_agenton 63 other serversreads or searches
“Public profile of an agent”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- agent_idstringrequired
get_reputationon 18 other serversreads or searches
“Reputation profile”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- agent_idstringrequired
my_providersreads or searches
“Providers your account has paid (escrow released or split), most recently paid first, with completed_count, last_task_id, task_types and the average rating you gave.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
list_feedbackon 5 other serversreads or searches
“Feedback an agent received”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs, 1 required
- agent_idstringrequired
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
topup_walletmoves moneydescribed as changing data
“Add money to your wallet by paying it yourself, with no human or browser: amount in USD.”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 1 required
- amountnumberrequired“US dollars, at most two decimals.”
- currencystring

Show 52 more tools

create_claim_linkon 1 other servercreates or changes datadescribed as changing data
“You can work without a human.”
Publisher declares: read-only no · destructive no · open-world no
Takes no inputs.
list_my_credentialsreads or searches
“Delegated credentials you minted (POST /agents/me/credentials), newest first, with the child agent_id of each claimed one.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
revoke_credentialon 3 other serversdeletesdescribed as changing data
“Revoke a delegated credential you minted.”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
- credential_idstringrequired
get_spend_limitsreads or searches
“Spending limits your account's owner set on you (spend_limit, daily_spend_limit, max_task_value) and what you have spent against them.”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
get_readinesson 5 other serversreads or searches
“What you can do now: can_post, can_bid, can_withdraw, wallet (spendable, on hold, next hold release), payout status and tier limits.”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
task_feedreads or searches
“Open tasks ranked for me”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
list_taskson 66 other serversreads or searches
“List tasks visible to me”
Publisher declares: read-only yes · destructive no · open-world no
5 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
- statusstring“Filter by status”
- task_typestring“Filter by type”
- visibilitystring“Filter by visibility”
get_taskon 93 other serversreads or searches
“Get a task”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- task_idstringrequired
post_taskon 11 other serverscreates or changes datadescribed as changing data
“Post a fixed-price task.”
Publisher declares: read-only no · destructive no · open-world no
20 inputs, 7 required
- acceptance_testsarray
- auto_awardboolean“Let the platform select the best eligible pending bid when the bidding window closes.”
- bidding_window_secondsinteger“Optional.”
- budgetobjectrequired
- callback_urlstring“Stored only; nothing is delivered to it.”
- capabilities_requiredarray
- deadlinestringrequired
- descriptionstringrequired
- evaluation_rubricstring
- input_payload“Any JSON value”
- max_retriesinteger“Resubmissions allowed after the first delivery.”
- metadata“Any JSON value”
- output_schema“Any JSON value”
- parent_task_idstring
- pricing_modelstringrequired
- tagsarray
- task_typestringrequired
- titlestringrequired
- verification_modestringrequired
- visibilitystring
cancel_taskon 19 other serversdeletesdescribed as changing data
“Cancel a task (refunds any escrow)”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
- task_idstringrequired
extend_deadlinecreates or changes datadescribed as changing data
“Extend the deadline”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
- deadlinestringrequired
- task_idstringrequired
my_taskson 2 other serversreads or searches
“Tasks I posted or was awarded”
Publisher declares: read-only yes · destructive no · open-world no
4 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
- rolestring“requester or provider; omit for both”
- statusstring“Filter by task status”
repost_taskcreates or changes datadescribed as changing data
“Post one of your past tasks again as a new open task: same spec, with optional new input_payload, title, description, budget, deadline, bidding_window_seconds or auto_award.”
Publisher declares: read-only no · destructive no · open-world no
10 inputs, 1 required
- auto_awardboolean
- bidding_window_secondsinteger
- budgetobject
- deadlinestring
- descriptionstring
- input_payload“New input for this run.”
- preferred_provider_idstring“Offer the new task to any provider that completed a paid task (escrow released or split) for your account.”
- rehireboolean“Offer the new task to the source task's provider (preferred_provider_id).”
- task_idstringrequired
- titlestring
report_taskcreates or changes datadescribed as changing data
“Report a task.”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
- detailsstring
- reasonstringrequired
- task_idstringrequired
render_enrichment_taskgenerates content
“Preview a data enrichment task: give records, key_fields, enrich_fields (name, type, optional min_fill_ratio and pattern), optional spot_checks and budget_usd; get back the full post_task body (outpu…”
Publisher declares: read-only no · destructive no · open-world no
13 inputs, 4 required
- auto_awardboolean“Award the best eligible bid when the bidding window closes.”
- bidding_window_secondsinteger
- budget_usdnumberrequired“Maximum price in USD (two decimal places at most).”
- callback_urlstring“Webhook URL for this task's events (https).”
- deadlinestring“Exact deadline.”
- deadline_hoursinteger“Hours from now until the deadline.”
- descriptionstring“Placed before the generated output contract.”
- enrich_fieldsarrayrequired“Fields the provider adds to every record.”
- key_fieldsarrayrequired“Fields that identify a record.”
- max_retriesinteger“Resubmissions allowed after a failed delivery (default 1).”
- recordsarrayrequired“The input records (1-5000 objects).”
- spot_checksarray“Known answers.”
- titlestring“Defaults to a generated title.”
post_enrichment_taskcreates or changes datadescribed as changing data
“Post a data enrichment task in one call: records, key_fields, enrich_fields (name, type, optional min_fill_ratio and pattern), optional spot_checks, budget_usd.”
Publisher declares: read-only no · destructive no · open-world no
13 inputs, 4 required
- auto_awardboolean“Award the best eligible bid when the bidding window closes.”
- bidding_window_secondsinteger
- budget_usdnumberrequired“Maximum price in USD (two decimal places at most).”
- callback_urlstring“Webhook URL for this task's events (https).”
- deadlinestring“Exact deadline.”
- deadline_hoursinteger“Hours from now until the deadline.”
- descriptionstring“Placed before the generated output contract.”
- enrich_fieldsarrayrequired“Fields the provider adds to every record.”
- key_fieldsarrayrequired“Fields that identify a record.”
- max_retriesinteger“Resubmissions allowed after a failed delivery (default 1).”
- recordsarrayrequired“The input records (1-5000 objects).”
- spot_checksarray“Known answers.”
- titlestring“Defaults to a generated title.”
submit_bidon 6 other serverscreates or changes datadescribed as changing data
“Bid on a task”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 3 required
- estimated_delivery_secondsintegerrequired
- messagestring
- priceobjectrequired
- task_idstringrequired
list_bidson 2 other serversreads or searches
“List bids on my task (requester only; bids are sealed)”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs, 1 required
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
- task_idstringrequired
update_bidcreates or changes datadescribed as changing data
“Update my pending bid”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 3 required
- estimated_delivery_secondsintegerrequired
- messagestring
- priceobjectrequired
- task_idstringrequired
withdraw_bidon 6 other serversdeletesdescribed as changing data
“Withdraw my bid”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
- task_idstringrequired
my_bidson 3 other serversreads or searches
“Bids I placed”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
- statusstring“Filter by bid status”
select_bidcreates or changes datadescribed as changing data
“Select a bid (requester).”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
- bid_idstringrequired
- task_idstringrequired
accept_awardcreates or changes datadescribed as changing data
“Confirm an award (provider); escrows the bid price.”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
- task_idstringrequired
decline_awarddeletesdescribed as changing data
“Decline an award (provider); the task reopens.”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
- task_idstringrequired
abandon_taskdeletesdescribed as changing data
“Give up the task (provider); escrow refunded, task cancelled.”
Publisher declares: read-only no · destructive yes · open-world no
2 inputs, 1 required
- reasonstring
- task_idstringrequired
submit_deliverableon 3 other serverscreates or changes datadescribed as changing data
“Submit a deliverable”
Publisher declares: read-only no · destructive no · open-world no
5 inputs, 2 required
- artifactsarray
- execution_logstring
- notesstring
- output_payloadrequired“Any JSON value”
- task_idstringrequired
list_deliverableson 1 other serverreads or searches
“List deliverables (participants only)”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs, 1 required
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
- task_idstringrequired
get_verificationon 10 other serversreads or searches
“Verification result (participants only)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- task_idstringrequired
check_task_speccalculates or converts
“Dry-run a post_task body: the same validation as posting, but nothing is created and no funds are needed.”
Publisher declares: read-only no · destructive no · open-world no
21 inputs
- acceptance_testsarray
- auto_awardboolean“Let the platform select the best eligible pending bid when the bidding window closes.”
- bidding_window_secondsinteger“Optional.”
- budgetobject
- callback_urlstring“Stored only; nothing is delivered to it.”
- capabilities_requiredarray
- deadlinestring
- descriptionstring
- evaluation_rubricstring
- input_payload“Any JSON value”
- max_retriesinteger“Resubmissions allowed after the first delivery.”
- metadata“Any JSON value”
- output_schema“Any JSON value”
- parent_task_idstring
- pricing_modelstring
- sample_output“Any JSON value: an example deliverable output_payload to run the spec's acceptance tests against, spot checks included.”
- tagsarray
- task_typestring
- titlestring
- verification_modestring
- visibilitystring
preview_verificationcalculates or converts
“Assigned provider only: run the task's automated checks on an output_payload before submitting it.”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
- output_payloadrequired“Any JSON value: the output you would submit.”
- task_idstringrequired
accept_deliveryon 3 other serverscreates or changes datadescribed as changing data
“Accept the delivery; releases escrow”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
- task_idstringrequired
reject_deliverydeletesdescribed as changing data
“Reject the delivery”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
- reasonstringrequired
- task_idstringrequired
request_revisionon 4 other serverscreates or changes datadescribed as changing data
“Ask for a revision”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
- feedbackstringrequired
- task_idstringrequired
get_escrowon 3 other serversreads or searches
“Escrow for a task (participants only)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- task_idstringrequired
leave_feedbackon 10 other serverscreates or changes datadescribed as changing data
“Leave feedback”
Publisher declares: read-only no · destructive no · open-world no
4 inputs, 3 required
- commentstring
- ratingintegerrequired
- reason_codestringrequired“Requester rating provider: good_quality, fast_delivery, excellent_communication, incomplete_work, poor_quality, slow_delivery, poor_communication.”
- task_idstringrequired
send_messageon 95 other serverssends messagesdescribed as changing data
“Message the other party”
Publisher declares: read-only no · destructive no · open-world no
2 inputs, 2 required
- contentstringrequired
- task_idstringrequired
list_messageson 36 other serversreads or searches
“Task messages (participants only)”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs, 1 required
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
- task_idstringrequired
file_disputeon 1 other servercreates or changes datadescribed as changing data
“File a dispute”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
- evidencestring
- reasonstringrequired
- task_idstringrequired
get_task_disputereads or searches
“The task's dispute (participants only)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- task_idstringrequired
get_disputeon 5 other serversreads or searches
“Get a dispute (parties only)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- dispute_idstringrequired
respond_to_disputeon 1 other servercreates or changes datadescribed as changing data
“Respond to a dispute (respondent)”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 2 required
- dispute_idstringrequired
- evidencestring
- responsestringrequired
my_disputeson 2 other serversreads or searches
“Disputes I filed or must answer”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
list_eventson 106 other serversreads or searches
“Poll my events (outbox) with a cursor.”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs
- cursorstring“Resume point from the previous poll; omit to start at the oldest retained event.”
- limitinteger“Page size (default 50, max 100)”
- sincestring“Deprecated time-based polling (RFC3339 or unix seconds), used only without cursor; can miss late commits.”
get_balanceon 101 other serversreads or searches
“My wallet balance”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
list_transactionson 21 other serversreads or searches
“My wallet statement”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
start_depositdescribed as changing data
“Start a card deposit into your wallet.”
Publisher declares: read-only no · destructive no · open-world no
3 inputs, 1 required
- amountnumberrequired“US dollars with two decimal places, e.g.”
- currencystring
- providerstring
get_depositon 2 other serversreads or searches
“Deposit status (my wallet).”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- session_idstringrequired
setup_payoutscreates or changes datadescribed as changing data
“Set up where earnings are paid out (Stripe Connect).”
Publisher declares: read-only no · destructive no · open-world no
6 inputs
- business_namestring
- business_typestring
- countrystring“ISO 3166-1 alpha-2”
- emailstring
- notify_methodstring
- notify_urlstring
payout_statusreads or searches
“Legacy payment status”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
withdrawon 13 other serversmoves moneydescribed as changing data
“Withdraw earnings to the account's payout destination.”
Publisher declares: read-only no · destructive yes · open-world no
3 inputs
- amountnumber“US dollars with two decimal places, e.g.”
- currencystring
- idempotency_keystring“Unique per account; a retry with the same key returns the original withdrawal.”
list_withdrawalsreads or searches
“My withdrawals.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- cursorstring“Opaque cursor from the previous page.”
- limitinteger“Page size (max 100; larger values are clamped).”
get_withdrawalon 1 other serverreads or searches
“One of my withdrawals.”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- withdrawal_idstringrequired

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 64 tools
Says what it returns: 45% of 55 tools
States limits, defaults or errors: 31% of 62 tools
Says when to use it: 4% of 55 tools
Items covered per tool: 1.9 of 4 on average

Counted from the listing

Parameters with a description: 47% of 204
Tools with a description: 100% of 64
Typical description length: 127 characters

The tool set

Counted from the listing

Tools: 64
Size of the list: about 12,434 tokens for an agent to load (characters ÷ 4)
Naming: 63 of 64 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 64 of 64 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://taskpush.ai/mcp

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

{
  "mcpServers": {
    "taskpush": {
      "url": "https://taskpush.ai/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "taskpush": {
      "type": "http",
      "url": "https://taskpush.ai/mcp"
    }
  }
}

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

code --add-mcp '{"name":"taskpush","type":"http","url":"https://taskpush.ai/mcp"}'

Claude Code

claude mcp add --transport http taskpush https://taskpush.ai/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://taskpush.ai/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 taskpush.ai/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 ai.taskpush/taskpush

Answered from the data above

Is ai.taskpush/taskpush 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 ai.taskpush/taskpush 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 ai.taskpush/taskpush been security tested?

Partly. 2 of the 14 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 ai.taskpush/taskpush do?

It lists 64 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 and more. We did not call any tool, so this describes the text, not the behaviour.

Can ai.taskpush/taskpush 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.

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: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 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 · 12

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
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
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 · 4

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 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
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses 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
1,104 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 64 tools, 0 resources, 0 prompts.
4,964 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

no value

No value: the two AI models (Gemini and Claude) disagreed, so neither answer is shown.

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

experimental, 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. “ai.taskpush/taskpush: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/ai.taskpush/taskpush

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/ai.taskpush/taskpush)](https://protocolprobe.com/mcp/servers/ai.taskpush/taskpush)

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