MCP Server

Stale

io.github.Cranot/agentskb MCP Server

io.github.Cranot/agentskb

Expert-researched answers from official sources for AI agents, no signup required.

What is the io.github.Cranot/agentskb MCP server?

The AgentsKB MCP server provides AI agents with access to a curated knowledge base of 55,000+ expert-quality answers sourced from official documentation, specs, and RFCs across 287 domains. It offers researched answers rather than search results, with particular depth in databases, frameworks, and infrastructure tooling. The server is hosted and requires no local setup or API key.

AgentsKB gives your AI agent access to canonical, researched answers to technical problems. Rather than searching the web, it provides expert-vetted responses sourced from official documentation and specifications. It covers 55,000+ Q&As across domains like PostgreSQL, Next.js, Docker, and Bash, with the ability to queue new topics for research if coverage doesn't yet exist.

How to install io.github.Cranot/agentskb

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agentskb": {
      "command": "npx",
      "args": [
        "-y",
        "@agentskb/cli"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

ask_question — Get expert-quality answers with sources; accepts question, optional domain filter, and result limit
preflight_check — See what verified knowledge exists for a given task before diving in
search_questions — Browse Q&As by topic or query across the knowledge base
get_stats — Retrieve live coverage metrics across all domains
consult_taxonomy — Navigate and explore the knowledge taxonomy by path
check_prerequisites — Find foundational topics you should understand first for a given domain
get_lockfile_status — Check whether strict/pinned-answer mode is active

Use cases

Get authoritative answers to PostgreSQL, Prisma, or Drizzle questions with official source citations
Research Next.js, NextAuth, or Vue framework patterns before implementing features
Understand Docker, Bash, nginx, or Git best practices from canonical sources
Verify prerequisites and foundational knowledge before tackling complex infrastructure tasks
Browse curated Q&As to learn domain-specific patterns without web search

io.github.Cranot/agentskb MCP server FAQ

What is AgentsKB?

AgentsKB is a hosted MCP server that provides AI agents with expert-researched answers from official sources (docs, specs, RFCs) across 55,000+ Q&As in 287 domains. It prioritizes accuracy over coverage and queues new topics for research if not yet covered.

Is AgentsKB free?

Yes, the MCP server at https://mcp.agentskb.com/mcp-kb requires no API key, signup, or payment.

How do I install it in Claude Desktop or Cursor?

Add the server to your MCP config file (claude_desktop_config.json for Claude Desktop, ~/.cursor/mcp.json for Cursor) with type 'http' and url 'https://mcp.agentskb.com/mcp-kb'. See the README for per-project config locations.

What domains does AgentsKB cover best?

Deepest coverage is in PostgreSQL, Prisma, Drizzle, Next.js, NextAuth, Vue, Docker, Bash, nginx, and Git. Coverage is uneven and growing; call get_stats for live counts.

What happens if I ask about a topic that isn't covered?

The server queues it for research and replies 'Topic <name> research queued' — you can ask again later once research is complete.

Can I use AgentsKB without an MCP client?

Yes, there's a plain HTTP REST API at https://agentskb-api.agentskb.com/api/free/ask that requires no key or client setup.

README (reference)

Source of truth, from the repository.

AgentsKB MCP Server

Give Your AI Expert-Level Knowledge

Researched answers to any problem. Your AI, upgraded.

About this repository: AgentsKB is a hosted MCP server — there is no server to build or run locally, and this repository contains no source code. It exists to document the endpoint and to collect bug reports. Point your MCP client at the URL below and you are done.

Installation

The server is hosted at https://mcp.agentskb.com/mcp-kb and speaks MCP over streamable HTTP. No API key and no signup are required.

Claude Code

claude mcp add --transport http agentskb https://mcp.agentskb.com/mcp-kb

Add --scope user to make it available in every project instead of just the current one. Verify the connection with:

claude mcp list

Claude Desktop, Cursor, Cline, and other MCP clients

Add this to your client's MCP configuration file:

{
  "mcpServers": {
    "agentskb": {
      "type": "http",
      "url": "https://mcp.agentskb.com/mcp-kb"
    }
  }
}

Config file locations:

Client	File
Claude Code (per-project)	`.mcp.json` in the project root
Claude Code (global)	`~/.claude.json`
Claude Desktop	`claude_desktop_config.json`
Cursor (global)	`~/.cursor/mcp.json`
Cursor (per-project)	`.cursor/mcp.json` in the project root

Cursor does not use the type field — for Cursor, list url on its own.

Some older clients do not support remote HTTP servers and only launch local processes. If yours is one of them, bridge to the endpoint with mcp-remote:

{
  "mcpServers": {
    "agentskb": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.agentskb.com/mcp-kb"]
    }
  }
}

REST API (no MCP client)

The knowledge base is also reachable over plain HTTP, with no key:

curl -X POST https://agentskb-api.agentskb.com/api/free/ask \
  -H "Content-Type: application/json" \
  -d '{"question":"What is a PostgreSQL index scan?"}'

What makes us different

Your AI searches. We research. That's the difference.

Dedicated research per question - not a side task while debugging
Official sources only - docs, specs, RFCs
Would rather not answer than guess wrong

Tools

Tool	Arguments	Description
`ask_question`	`question`*, `domain`, `limit`	Expert-quality answers with sources
`preflight_check`	`task`*, `depth`	See what verified knowledge exists for your task
`search_questions`	`query`*, `domain`, `limit`	Browse Q&As by topic
`get_stats`	—	Coverage metrics
`consult_taxonomy`	`path`, `depth`	Navigate the knowledge taxonomy
`check_prerequisites`	`domain`*	Foundational topics to understand first
`get_lockfile_status`	—	Check whether strict/pinned-answer mode is active

* required. question and query expect a full natural-language question — bare keywords such as mysql are rejected.

The server also exposes two resources: agentskb://context/current (detected project stack) and agentskb://context/prompt (a system-prompt fragment for that stack).

Coverage

55,000+ Q&As across 287 domains. The deepest coverage today is:

Databases and ORMs: PostgreSQL, Prisma, Drizzle
Frameworks: Next.js, NextAuth, Vue
Infrastructure and tooling: Docker, Bash, nginx, Git

Call get_stats for live counts, or consult_taxonomy to browse the full domain list.

Coverage is uneven and still growing. If you ask about a topic that is not yet covered, the server queues it for research and replies Topic '<name>' research queued instead of returning an answer — ask again later.

Reporting bugs

Open an issue on this repository: https://github.com/Cranot/agentskb-mcp/issues

Website: https://agentskb.com
@agentskb/cli on npm: https://www.npmjs.com/package/@agentskb/cli — a separate tool for pinning and verifying answers in a repo (init, check, lock, request, update, verify). It does not implement an MCP server and is not needed to use the endpoint above.

License

MIT

Related MCP servers

DocRocket

Generate on-brand proposals, reports, and contracts instantly. Auto-extracts brand from any URL.

Pusher Channels

Active

Trigger events, query channels, and manage realtime messaging on Pusher Channels.

TypeScript

MIT

View repository →

io.github.Crawleo/Crawleo-MCP

Stale

Real-time web search and content extraction for AI assistants via MCP.

JavaScript

MIT

View repository →

io.github.CrazymakER23/convergealpha

AI stock signal convergence � 13 sources, Bayesian scoring, verified outcomes.

View repository →

Createya — AI Image & Video Generation

Maintained

100+ AI models: FLUX, Sora, Veo, Kling, Runway, Suno. OAuth or Bearer. No VPN. RU billing.

Shell

MIT

View repository →

io.github.Creativestefan/mailbridge

Active

Connect your AI assistant to email — read, search, send, and organise via IMAP/SMTP.

JavaScript

MIT

View repository →