Agentcontext MCP server

by mbeato·io.github.mbeato/agentcontext·v0.1.2

No reviews yet

Normalize AGENTS.md / CLAUDE.md / .cursor/rules / .clinerules / .windsurf/rules from one source.

A88/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A88/100

full report

Adoption

New

0 stars47 downloads/wk

Reviews

Write one

Nobody has reviewed Agentcontext yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agentcontext tools (2)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

convert_agent_context
Convert an agent-context IR (returned by read_agent_context) to one or more target formats. Returns rendered file contents keyed by repo-relative path.
read_agent_context
Parse all agent-context files in a repo (CLAUDE.md, AGENTS.md, .cursor/rules, .clinerules, .windsurf/rules, .aider.conf.yml, etc.) and return a unified IR. Use this to see what rules a project has across every AI-coding-tool format.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings

Code scan3 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 36 days ago12/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Agentcontext compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 88/100; higher than 75% of 48,255 servers
Tools: 2; the typical server has 7
Tools that change things: 0%; typical: 0%. Fewer write tools means less an agent can break
Downloads a week: 47; more than 39% of 12,191 servers with a package

What its tools let an agent do: 2 read

Install Agentcontext in Claude Code, Cursor or VS Code

Runs npx -y @mbeato/agentcontext-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agentcontext -- npx -y @mbeato/agentcontext-mcp

Add to Cursor

What the publisher says

From the Agentcontext repository's README, as published. We do not edit it. Read it on GitHub

@mbeato/agentcontext-mcp

MCP server for @mbeato/agentcontext — normalize agent-context files (AGENTS.md, CLAUDE.md, GEMINI.md, .cursor/rules/.mdc, .windsurf/rules/.md, .clinerules/*.md, CONVENTIONS.md) from any MCP-aware coding agent.

Two tools exposed:

readagentcontext(path) — parse all detected formats in a repo, return one unified IR.
convertagentcontext(ir, targets) — render the IR to one or more target formats; returns the file map.

Install

// ~/.config/claude-code/mcp.json (or your MCP client's config)
{
  "mcpServers": {
    "agentcontext": {
      "command": "npx",
      "args": ["-y", "@mbeato/agentcontext-mcp"]
    }
  }
}

Status

v0.1 — early. See https://agentsmd.apimesh.xyz for the project home.

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Agentcontext: common questions

Is Agentcontext MCP server safe?: Yes, by our scan: it is graded A (88/100). Read the Agentcontext safety report
How do I install Agentcontext?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agentcontext need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agentcontext maintained?: The last commit was 74 days ago (2026-08-22). The latest release is v0.1.2.
How does Agentcontext compare with other MCP servers?: safety score 88/100 (higher than 75% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.