Agentskb Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Agentskb Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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.
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 mcp add --transport http agentskb https://mcp.agentskb.com/mcp-kbAdd --scope user to make it available in every project instead of just the current one. Verify the connection with:
claude mcp listAdd 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"]
}
}
}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?"}'Your AI searches. We research. That's the difference.
| 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).
55,000+ Q&As across 287 domains. The deepest coverage today is:
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.
Open an issue on this repository: <https://github.com/Cranot/agentskb-mcp/issues>
@agentskb/cli on npm: <https://www.npmjs.com/package/@agentskb/cli> — aseparate 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.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.