Skip to main content
Glama
124,556 servers. Updated
Browse by product
20 Best Documentation MCP Servers: compared and ranked, November 2026Ranked from 2,605 matching servers on stars, growth, downloads and maintenance. Updated .

Matching MCP tools:

Matching MCP Connectors:

"A server to add framework documentation and use a cursor agent to search it" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    C
    maintenance
    Lets AI agents turn a repository's git history into proposed GitHub issues grouped into units of work, each with a commit checklist and links, then create and close them only after approval. Planning is read-only and creation defaults to a dry run, skipping anything that already exists.
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    One-pass agentic inbox triage as an MCP server: fetch unread Gmail → classify (action_needed/fyi/newsletter/noise) → summarize → extract tasks → draft replies as Gmail DRAFTS (never sends) → flag calendar → write a triage report. Four stdio tools (fetch_emails, save_gmail_draft, append_tasks, write_report); the host is the LLM, so it runs keyless in Claude Code. Gmail scopes: readonly + compose
    4
    17 PyPI
    3
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    A single source of truth for a product's state, roadmap, and deferred work, read and written equally by you and your AI agent via web dashboard and MCP.
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that audits a project for documentation, rules, skills, and knowledge artifacts, compares against a reference concept catalog, and generates a prescription plan with frontmatter todos to guide creation of missing or incomplete elements.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Connects IDEs and coding agents to a task-management service, enabling them to read and manage tasks and record manual steps for approvals, credentials, or console actions so later sessions can resume.
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables an AI assistant to manage a simple to-do list stored in a local JSON file, with tools to add, list, get, complete, and delete tasks, plus a read-only pending tasks resource.
    -
  • F
    license
    A
    quality
    B
    maintenance
    Enables async-first working practices by providing tools to draft decision docs, convert meetings to async artifacts, score status updates, and triage sync vs async tasks. It also offers reference tools for the Open and Async book's principles and coaching prompts.
    11
    74 npm
    51
    -
  • A
    license
    B
    quality
    B
    maintenance
    Enables Claude to create, read, update and delete Microsoft To Do lists, tasks and checklist items, and Microsoft Planner plans, buckets and tasks, through Microsoft Graph as the signed-in user. Lists, plans and buckets can be referenced by ID or exact name, with destructive deletes requiring confirmation.
    31
    MIT
  • A
    license
    B
    quality
    C
    maintenance
    Lets Claude and other AI clients read and modify Microsoft To Do through natural language, adding, completing, searching, updating, and deleting tasks and sub-steps by title and list name instead of ids. Personal Microsoft accounts need no Azure app registration — a single device-code sign-in grants access, with optional read-only and no-delete modes available.
    18
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables an MCP-capable coding agent to run a local-first job search: recording verified opportunities in a private SQLite tracker, tracking follow-ups and outcomes, and preparing evidence-based resumes, application answers, and outreach drafts. It keeps all personal data on the user's machine and stops before submitting applications, uploading documents, or contacting anyone.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    MCP server enabling AI agents to interact with OpenProject API v3 for project management, including creating and managing work packages, projects, comments, time entries, boards, and user dashboards.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    A hosted MCP server that lets an owner's AI agent register, prove its X account via Sign in with X, discover the agents of X mutuals who have joined, and then propose, accept, and discuss shared goals on threaded tasks. Agents can post updates, escalate decisions to their humans, and draft (never send) payments, with all other agents' text returned as untrusted content.
    10
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI coding agents to coordinate through a local, pull-only message board by registering sessions, posting updates, proposing and accepting tasks, holding leases, and reading or acknowledging updates under scoped human authorization.
    8
    MIT
  • A
    license
    B
    quality
    C
    maintenance
    Enables AI assistants to manage Bitrix24 CRM entities, tasks, project kanban boards, and Scrum sprints through an incoming webhook, requiring explicit user confirmation for all write operations.
    31
    MIT
  • A
    license
    C
    quality
    C
    maintenance
    Enables AI agents to create and manage small project plans—including tasks, assignees, status, progress, dates, and dependencies—and retrieve Gantt-friendly project views over MCP stdio. State is stored in SQLite without external dependencies.
    10
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables multiple AI coding agents on different machines to coordinate on a single codebase by atomically claiming tasks, acquiring repo-relative file locks, and exchanging messages through a shared, token-authenticated SQLite-backed board over MCP.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to manage Kanban boards, cards, sessions, and automations through a unified MCP interface with real-time updates, supporting delegation, agent sessions, and human-in-the-loop interactions.
    AGPL 3.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Attaches a file-based kanban workflow to any project, allowing agents to create, claim, complete, and block work items using git as the locking mechanism.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to maintain project continuity through a file-based state hub with tasks, phases, and handoff snapshots. Provides MCP tools for reading and updating project state, with gatekeeping enforced via real-state evaluation and per-tool authorization.
    3
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables any MCP-capable coding agent to share one plain-Markdown project state — goals, tasks, decision logs, and session handoffs — stored in a project's .apm/ directory, with lock-safe concurrent writes and consistency checks that flag stale, blocked, or unowned work. This lets multiple agents and a human CLI resume work across interrupted sessions without a database or external service.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables people and their AI agents to share a kanban board whose tasks, hand-offs, reviews, notes and alerts live as markdown files in a private GitHub repo, with per-person access control. Works from Claude, ChatGPT, Claude Code, Codex or any MCP-speaking client, and can draw the board inside chats.
    AGPL 3.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    An MCP server enabling AI coding agents to interact with a task tracker that enforces rules server-side, replacing markdown files and hooks with a database, CLI, and web UI.
    2
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A task orchestration system for AI agent teams that provides a Kanban dashboard and 12 MCP tools to manage multi-step workflows with DAG dependencies. It enables agents to coordinate through task threads, automated retries, and real-time webhook notifications.
    34
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    MCP server for Agent Room, enabling AI agents to join shared meeting rooms and collaborate with humans via tools like room_listen and room_task_*.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables pipeline-driven task management for AI coding agents, with stage-gated workflows, dependency tracking, artifact versioning, and multi-agent collaboration.
    262 npm
    24
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables any MCP-capable agent to maintain a shared .apm Markdown source of truth for project goals, tasks, decisions, handoffs, and health insights. It lets multiple agents and CLI/dashboard tools coordinate using the same file-based read/write logic without a database.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables coding agents from different apps and subscriptions to coordinate as one team over Streamable HTTP, sharing goals, atomic task claims, handoffs, and messages, with questions routed to the owner and answered on a live web board. Each agent reads only what is new to it and can block on a wait call instead of polling a shared file.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI coding agents on the same machine to exchange local messages, manage and claim tasks, and coordinate folder locks through stdio MCP tools backed by plain files. It runs without a network server or dependencies and supports concurrent agents.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    A local MCP server that lets Claude Code, Codex and Gemini agents post messages, mention each other, wait for replies without burning tokens, and share tasks that move from assigned to verified. It pairs with a local desktop window for writing tasks, following every conversation, monitoring agent models and quota, and sending owner-signed instructions.
    MIT