agentmods.dev

calm-mcp

calm-mcp is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from Eilodon/CALM. Its token cost is not measured, scanned A, original, MIT.

A local MCP server that gives coding agents a call graph and hash-checked view of a codebase. A call graph shows which functions or components depend on one another.

In plain words
What is it for?
It is for exploring how code connects, tracing callers and dependencies, and checking that viewed code matches its recorded hash.
Why use it?
It helps agents understand code relationships and verify code identity instead of relying only on text searches such as grep.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

not rated 16 yesterday A scan tokens not measured original MIT
View the source file Eilodon/CALM
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/eilodon/calm/calm-mcp
Clone the repo
git clone --depth 1 https://github.com/Eilodon/CALM

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for calm-mcp

README.md
[![agentmods](https://agentmods.dev/badge/mcp/eilodon/calm/calm-mcp.svg)](https://agentmods.dev/mcp/eilodon/calm/calm-mcp)
Your own site
<a href="https://agentmods.dev/mcp/eilodon/calm/calm-mcp"><img src="https://agentmods.dev/badge/mcp/eilodon/calm/calm-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

calm-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 10 lines

What it actually says

{
  "calm-mcp": {
    "command": "npx",
    "args": [
      "-y",
      "@eilodon/calm-mcp"
    ],
    "env": {}
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 10 lines scan A 08374f17c9b0

Subscribe to this mod's changes

calm-mcp is an MCP server published in the GitHub repository Eilodon/CALM (16 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-agentsai-codingcall-graphclaude-codecode-intelligencecoding-agent
Related

Other mcp servers, from other repositories

no_human

MCP server "nohuman" as configured in no-human-ai/nohuman. Launched with nh mcp-serve.

no-human-ai/no_human · not measured

no_human

Autonomous AI software-delivery orchestrator driving the Claude Agent SDK on your own Claude credentials. Runs locally from the no-human Python package.

no-human-ai/no_human · not measured

mako-ai

Agentmako is a local project intelligence CLI and MCP server for codebases and databases, with repo-aware indexing, schema snapshots, and secure live database connectivity. Runs locally from the agentmako npm package.

drhalto/agentmako · not measured

visor-mcp

Skill-Orchestrated Context Intelligence Engine for AI coding agents. Runs locally from the visor-mcp Python package.

dibun75/visor · not measured

ragcode

Local code intelligence foundation: structural code graph, LanceDB semantic layer, retrieval, context packing, and MCP tools. Runs locally from the ragcode-context-engine npm package.

MarshallEriksen-Neura/ragcode · not measured

codeindex

Self-contained, deterministic repo-indexing engine: walk + language detection + symbol/import extraction (tree-sitter AST with regex fallback) + import resolution + typed cross-file link-graph + analytics. Ships as a single zero-dependency engine.mjs that. Runs locally from the @maxgfr/codeindex npm package.

maxgfr/codeindex · not measured