Manufact

LeaderboardBack to leaderboard

Takibi

app.takibibase.com/mcp

Answers from your Takibi documents with citations, reads the tasks on your Takibi boards, and works them when the connection is allowed to.

View checks

Protocol: MCP 2026-07-28
Server version: 1.0.0
Website: takibibase.com
Supports: Tools

Overall score

How is this score calculated?

Last reviewed at Nov 11, 2026, 18:49:22 UTC

Server metadata

Pass100/100

Identity, discovery, and usage metadata advertised during the MCP handshake.

Stable server name

takibi

10/10Source

Human-readable title

Takibi

10/10Source

Useful description

Answers from your Takibi documents with citations, reads the tasks on your Takibi boards, and works them when the connection is allowed to.

20/20Source

Server version

Version 1.0.0

10/10Source

Public website

Website: takibibase.com

10/10Source

Scalable or high-resolution icon

1 icon advertised, including a scalable or high-resolution asset.

10/10Source

Server instructions

Usage instructions provided for agents.

20/20Source

Declared capabilities

Supports Tools.

10/10Source

Server instructions

Takibi holds the documents and task boards this connection can read. Call takibi_list_projects first to turn a collection name into its id. Ask with takibi_query and answer from its cited spans, naming the source document and reporting the support score. When nothing is cited or the spans do not answer the question, say the documents do not answer it; do not fill the gap from memory. Read a whole document with takibi_get_document only when a citation needs more context, and say so if the text came back cut. Read a task with takibi_get_task, and open its artifacts (deliverables, Founder feedback) with takibi_show_artifact. When the claim tools are present: claim one task at a time and keep notes short; each tool says which moves it allows. Tasks in review never close over this connection: they are accepted and closed in the Takibi app or CLI. A refused call says what to fix: when the fix is yours (retry, reclaim, shorten, rework), do it; otherwise pass it on to the person.

Discoverability

33/100

Client listings and public setup information.

mcp.json or server-card.json

Either mcp.json or an MCP Server Card declaring this endpoint passes.

The MCP Server Card declares this server's exact endpoint.

FoundSource

Setup instructions at MCP URL

The MCP endpoint publishes connection instructions for this server.

FoundSource

ChatGPT

No ChatGPT listing has been confirmed yet.

UnverifiedHow to get listed

Claude

No Claude listing has been confirmed yet.

UnverifiedHow to get listed

CursorGrok BotGrok

No Cursor marketplace listing has been confirmed yet.

UnverifiedHow to get listed

Muse

No Muse listing has been confirmed yet.

UnverifiedHow to get listed

4 unverified checks. Unverified checks earn no points until confirmed.

Protocol

Pass100/100

Connection, authentication, and protocol compatibility.

Resources list responds

0 resource(s) returned

Source

MCP negotiation succeeds (v1/v2)

MCP modern negotiation succeeded in 455ms

Source

Tools list returns results

5 tool(s) returned

Source

Server declares tools capability

Server declares tools capability in initialize response

Source

Tools

Pass100/100

Tool definitions, annotations, and client compatibility.

Skills over MCP resources are readable

Server does not advertise the Skills over MCP extension

Tool names follow the MCP 1–128 character range

All tool names follow the MCP recommended length

Source

All tools have OpenAI behavior hints

All tools declare the three OpenAI behavior hints as booleans

Source

Claude tools declare applicable behavior hints

All tools include an applicable readOnlyHint or destructiveHint

Source

All tools have descriptions

All tools have non-empty descriptions

Claude Code metadata fits its 2 KB fields

Tool descriptions and server instructions fit Claude Code's 2 KB fields

Source

All tools have a display title

Source

Cursor tool-name budget advisory

No tool name independently exhausts Cursor's observed 60-character combined budget

Observed behavior

Claude tool names are within 64 characters

All tool names are within Claude's 64-character limit

Source

Tool names use valid characters

All tool names use valid characters

Source

Tool names follow MCP uniqueness guidance

All tool names are unique

Source

Tool input schemas have a valid object structure

All tool input schemas have a valid object structure

Source

OpenAI file parameters use valid schemas

All declared OpenAI file parameters use reviewer-valid schemas

Source

Tool text has no hidden control characters

No invisible or control characters found in tool-facing text

Source

ChatGPT tool names are unique

All tool names are unique

Source

Declared output schemas have a valid basic structure

0 declared output schema(s) pass basic structural validation; schemas may describe any JSON value, including arrays

Source

Tool input header annotations are valid

All x-mcp-header annotations satisfy Streamable HTTP requirements

Source

MCP Apps

Not applicableOptional

App resources, metadata, and rendering requirements.

All discovered view resources were inspected

No view resources found — view checks skipped

Source

View resource envelope is valid

No view resources found — view checks skipped

Declared domains respond

No view resources found — view checks skipped

Tool visibility metadata is valid

No view resources found — view checks skipped

Source

Tool-linked resource URI is readable

No view resources found — view checks skipped

Source

Tool invocation metadata present

No view resources found — view checks skipped

Source

CSP metadata covers literal external origins

No view resources found — view checks skipped

Source

View resource metadata complete

No view resources found — view checks skipped

Source

View resources declare a domain

No view resources found — view checks skipped

Source

Views do not request nested iframe domains

No view resources found — view checks skipped

Source

Tool documentation quality

84/100

How clearly each tool’s title, description, input and output schemas, and behavior annotations guide an agent.

takibi_queryTitles 89Descriptions 83Inputs 91Annotations 100Outputs 080/100

takibi_query

Title89/100

Ask Takibi

The title clearly communicates the tool’s action and subject. Keep it concise.

Description83/100

Answer a question from a Takibi collection the connected profile can access. Returns verbatim spans with citations plus a support score.

The description explains the capability, when to use it, and what to expect.

Inputs91/100

Input documentation gives an agent enough context to populate the arguments.

The question to answer from the collection.

Clear enough to supply this argument.

project

Collection id or exact name the profile can access.

Clear enough to supply this argument.

folder

Folder id to scope the ask to. Omit for the whole collection.

Clear enough to supply this argument.

How many passages to retrieve before the cited spans are picked (default 10). Raise it for broad questions that draw on many documents; lower it for a narrow lookup.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Ask Takibi",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "takibi_query",
  "title": "Ask Takibi",
  "description": "Answer a question from a Takibi collection the connected profile can access. Returns verbatim spans with citations plus a support score.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "q",
      "project"
    ],
    "properties": {
      "k": {
        "type": "integer",
        "maximum": 12,
        "minimum": 1,
        "description": "How many passages to retrieve before the cited spans are picked (default 10). Raise it for broad questions that draw on many documents; lower it for a narrow lookup."
      },
      "q": {
        "type": "string",
        "description": "The question to answer from the collection."
      },
      "folder": {
        "type": "string",
        "description": "Folder id to scope the ask to. Omit for the whole collection."
      },
      "project": {
        "type": "string",
        "description": "Collection id or exact name the profile can access."
      }
    }
  },
  "annotations": {
    "title": "Ask Takibi",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

takibi_list_projectsTitles 91Descriptions 98Inputs 100Annotations 100Outputs 087/100

takibi_list_projects

Title91/100

List Takibi collections

The title clearly communicates the tool’s action and subject. Keep it concise.

Description98/100

List the collections (and their visible folders) the connected profile can access. Returns each collection's id and name, with its folders' ids and names. Call before asking to resolve names to ids.

The description explains the capability, when to use it, and what to expect.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations100/100

All four behavior hints are declared.

{
  "title": "List Takibi collections",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "takibi_list_projects",
  "title": "List Takibi collections",
  "description": "List the collections (and their visible folders) the connected profile can access. Returns each collection's id and name, with its folders' ids and names. Call before asking to resolve names to ids.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {}
  },
  "annotations": {
    "title": "List Takibi collections",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

takibi_get_documentTitles 97Descriptions 97Inputs 96Annotations 100Outputs 087/100

takibi_get_document

Title97/100

Get Takibi document

The title clearly communicates the tool’s action and subject. Keep it concise.

Description97/100

Fetch one source document's text for grounding, from an answer citation. Returns the document id, its name, the extracted text (null when it has none) and whether the text was cut to maxChars.

The description explains the capability, when to use it, and what to expect.

Inputs96/100

Input documentation gives an agent enough context to populate the arguments.

documentId

Document id from an answer citation.

Clear enough to supply this argument.

project

Collection id or exact name holding the document.

Clear enough to supply this argument.

maxChars

How much of the document text to return, counted from its start (default 50000 characters). The reply says when the text was cut; raise it when a cited passage sits late in a long document.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Get Takibi document",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "takibi_get_document",
  "title": "Get Takibi document",
  "description": "Fetch one source document's text for grounding, from an answer citation. Returns the document id, its name, the extracted text (null when it has none) and whether the text was cut to maxChars.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "documentId",
      "project"
    ],
    "properties": {
      "project": {
        "type": "string",
        "description": "Collection id or exact name holding the document."
      },
      "maxChars": {
        "type": "integer",
        "maximum": 200000,
        "minimum": 1000,
        "description": "How much of the document text to return, counted from its start (default 50000 characters). The reply says when the text was cut; raise it when a cited passage sits late in a long document."
      },
      "documentId": {
        "type": "string",
        "description": "Document id from an answer citation."
      }
    }
  },
  "annotations": {
    "title": "Get Takibi document",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

takibi_get_taskTitles 100Descriptions 97Inputs 81Annotations 100Outputs 084/100

takibi_get_task

Title100/100

Get Takibi task

The title clearly communicates the tool’s action and subject. Keep it concise.

Description97/100

Fetch one task the connected profile can read, for grounding after a webhook wake. Returns its title, status, assignee, due date, blocked flag and reason, its artifact list (hand-ins, deliverables, Founder feedback), the latest review note, and its parent and follow-up tasks.

The description explains the capability, when to use it, and what to expect.

Inputs81/100

Input documentation gives an agent enough context to populate the arguments.

taskId

Task id from a webhook payload or board.

Clear enough to supply this argument.

project

Collection id or exact name holding the task.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Get Takibi task",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "takibi_get_task",
  "title": "Get Takibi task",
  "description": "Fetch one task the connected profile can read, for grounding after a webhook wake. Returns its title, status, assignee, due date, blocked flag and reason, its artifact list (hand-ins, deliverables, Founder feedback), the latest review note, and its parent and follow-up tasks.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "taskId",
      "project"
    ],
    "properties": {
      "taskId": {
        "type": "string",
        "description": "Task id from a webhook payload or board."
      },
      "project": {
        "type": "string",
        "description": "Collection id or exact name holding the task."
      }
    }
  },
  "annotations": {
    "title": "Get Takibi task",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

takibi_show_artifactTitles 94Descriptions 89Inputs 95Annotations 100Outputs 084/100

takibi_show_artifact

Title94/100

Show Takibi artifact

The title clearly communicates the tool’s action and subject. Keep it concise.

Description89/100

Read one artifact body (Founder feedback, deliverables) from a task the connected profile can read. Long notes come back in windows of maxChars: read on from nextFrom while it is not null.

The description explains the capability, when to use it, and what to expect.

Inputs95/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

taskId

Task id from a webhook payload, board, or takibi_get_task.

Clear enough to supply this argument.

artifactId

Artifact id from the task artifact list (Founder feedback via lastFeedbackArtifactId).

Clear enough to supply this argument.

project

Collection id or exact name holding the task.

Clear enough to supply this argument.

from

Where in the note to start reading (default 0, the beginning). To read on, pass the nextFrom value from the previous reply.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

maxChars

How much of the note to return in one window (default 50000 characters). Use a smaller window to skim a long note.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Show Takibi artifact",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "takibi_show_artifact",
  "title": "Show Takibi artifact",
  "description": "Read one artifact body (Founder feedback, deliverables) from a task the connected profile can read. Long notes come back in windows of maxChars: read on from nextFrom while it is not null.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "taskId",
      "artifactId",
      "project"
    ],
    "properties": {
      "from": {
        "type": "integer",
        "maximum": 9007199254740991,
        "minimum": 0,
        "description": "Where in the note to start reading (default 0, the beginning). To read on, pass the nextFrom value from the previous reply."
      },
      "taskId": {
        "type": "string",
        "description": "Task id from a webhook payload, board, or takibi_get_task."
      },
      "project": {
        "type": "string",
        "description": "Collection id or exact name holding the task."
      },
      "maxChars": {
        "type": "integer",
        "maximum": 200000,
        "minimum": 1000,
        "description": "How much of the note to return in one window (default 50000 characters). Use a smaller window to skim a long note."
      },
      "artifactId": {
        "type": "string",
        "description": "Artifact id from the task artifact list (Founder feedback via lastFeedbackArtifactId)."
      }
    }
  },
  "annotations": {
    "title": "Show Takibi artifact",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

Put your MCP to the test

A few tasks worth trying with this server, chosen from its reviewed tools. These have not been run.

01List Takibi collectionsList the collections (and their visible folders) the connected profile can access.
02Ask TakibiAnswer a question from a Takibi collection the connected profile can access.
03Get Takibi documentFetch one source document's text for grounding, from an answer citation.
04Get Takibi taskFetch one task the connected profile can read, for grounding after a webhook wake.
05Show Takibi artifactRead one artifact body (Founder feedback, deliverables) from a task the connected profile can read.

Want to run these tasks against your MCP server with us?

Test your MCP in Cloud Book a test call

Overview

Category: Productivity

FAQ

Takibi setup, tools, quality score, publishing readiness, and alternatives.

How do I add Takibi to Claude, ChatGPT, or Cursor?

Add Takibi to Claude, ChatGPT, or Cursor by connecting its remote MCP URL in each client's MCP settings. In Claude, add a custom connector. In ChatGPT, add an MCP app. In Cursor, add an MCP server under Settings. The MCP URL is https://app.takibibase.com/mcp.

Is Takibi MCP ready for ChatGPT and Claude?

As of November 11, 2026, Takibi scores 100/100 on Manufact's MCP publishing checklist. The scan meets ChatGPT publishing checks and meets Claude publishing checks. Passing these checks does not guarantee marketplace approval.

How clear is Takibi's MCP tool documentation?

As of November 11, 2026, Takibi scores 84/100 in Manufact's review of tool titles, descriptions, input and output schemas, and behavior annotations. The review covers 5 of 5 discovered tools. The quality score measures documentation clarity; runtime behavior and marketplace readiness require separate checks.

What are the best alternatives to Takibi?

As of November 12, 2026, alternatives to Takibi in productivity on the Manufact MCP leaderboard include AdaptlyPost, Notion MCP, Paperpal, VantagePeers, and Date Calculator.

Not your MCP?

Review any public or OAuth MCP server for protocol compatibility, tool documentation, and ChatGPT and Claude publishing readiness. No account required.

Get your MCP score

LeaderboardBack to leaderboardLeaderboardBack to leaderboard

Opening report…

Loading report overview

Server metadata

Loading server metadata

Discoverability

Loading discoverability

Protocol

Loading protocol

Tools

Loading tools

MCP Apps

Loading mcp apps

Tool documentation quality

Loading tool documentation quality

Title94/100

Show Takibi artifact

The title clearly communicates the tool’s action and subject. Keep it concise.

Description89/100

Read one artifact body (Founder feedback, deliverables) from a task the connected profile can read. Long notes come back in windows of maxChars: read on from nextFrom while it is not null.

The description explains the capability, when to use it, and what to expect.

Inputs95/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

taskId

Task id from a webhook payload, board, or takibi_get_task.

Clear enough to supply this argument.

artifactId

Artifact id from the task artifact list (Founder feedback via lastFeedbackArtifactId).

Clear enough to supply this argument.

project

Collection id or exact name holding the task.

Clear enough to supply this argument.

from

Where in the note to start reading (default 0, the beginning). To read on, pass the nextFrom value from the previous reply.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

maxChars

How much of the note to return in one window (default 50000 characters). Use a smaller window to skim a long note.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Show Takibi artifact",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "takibi_show_artifact",
  "title": "Show Takibi artifact",
  "description": "Read one artifact body (Founder feedback, deliverables) from a task the connected profile can read. Long notes come back in windows of maxChars: read on from nextFrom while it is not null.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "required": [
      "taskId",
      "artifactId",
      "project"
    ],
    "properties": {
      "from": {
        "type": "integer",
        "maximum": 9007199254740991,
        "minimum": 0,
        "description": "Where in the note to start reading (default 0, the beginning). To read on, pass the nextFrom value from the previous reply."
      },
      "taskId": {
        "type": "string",
        "description": "Task id from a webhook payload, board, or takibi_get_task."
      },
      "project": {
        "type": "string",
        "description": "Collection id or exact name holding the task."
      },
      "maxChars": {
        "type": "integer",
        "maximum": 200000,
        "minimum": 1000,
        "description": "How much of the note to return in one window (default 50000 characters). Use a smaller window to skim a long note."
      },
      "artifactId": {
        "type": "string",
        "description": "Artifact id from the task artifact list (Founder feedback via lastFeedbackArtifactId)."
      }
    }
  },
  "annotations": {
    "title": "Show Takibi artifact",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

Manufact

Server metadata

Discoverability

Protocol

Tools

MCP Apps

Tool docsTool documentation quality

Title89/100

Description83/100

Inputs91/100

Annotations100/100

Output schema0/100

Title91/100

Description98/100

Inputs100/100

Annotations100/100

Output schema0/100

Title97/100

Description97/100

Inputs96/100

Annotations100/100

Output schema0/100

Title100/100

Description97/100

Inputs81/100

Annotations100/100

Output schema0/100

Title94/100

Description89/100

Inputs95/100

Annotations100/100

Output schema0/100

Put your MCP to the test

Overview

Related MCP servers

FAQ

Not your MCP?

Server metadata

Discoverability

Protocol

Tools

MCP Apps

Tool documentation quality

Server metadata

Discoverability

Protocol

Tools

MCP Apps

Tool docsTool documentation quality

Title89/100

Description83/100

Inputs91/100

Annotations100/100

Output schema0/100

Title91/100

Description98/100

Inputs100/100

Annotations100/100

Output schema0/100

Title97/100

Description97/100

Inputs96/100

Annotations100/100

Output schema0/100

Title100/100

Description97/100

Inputs81/100

Annotations100/100

Output schema0/100

Title94/100

Description89/100

Inputs95/100

Annotations100/100

Output schema0/100

Put your MCP to the test

Overview

Related MCP servers

FAQ

Not your MCP?

Tool documentation quality

Tool documentation quality