osmmcp CLAUDE.md

osmmcp CLAUDE.md is an instructions file for coding agents from NERVsystems/osmmcp. It costs 2,107 tokens per session, scanned A, original, MIT.

Project instructions for osmmcp, a Go program that provides a server for connecting AI clients to tools through the MCP protocol. They cover building it, running it locally, enabling HTTP access, authentication, and monitoring.

In plain words
What is it for?
Use them to compile all packages or the main program, run it over standard input or HTTP, turn on debugging, configure authentication, and check its health.
Why use it?
They collect the commands and runtime options needed to build the server and connect it safely to different clients.

Instructions file

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 instructions/nervsystems/osmmcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/NERVsystems/osmmcp

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 osmmcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nervsystems/osmmcp/claude-md.svg)](https://agentmods.dev/instructions/nervsystems/osmmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nervsystems/osmmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nervsystems/osmmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,107 This file is loaded in full into every session.
When invoked 2,107 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02107 $0.02107
Opus 5 $0.01053 $0.01053
Sonnet 5 $0.00421 $0.00421
Haiku 4.5 $0.00211 $0.00211

Measured 5d ago against content hash 1cc19ff53584, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

osmmcp CLAUDE.md 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 5d 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.

CLAUDE.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build and Development Commands

Building

# Build all packages
go build -v ./...

# Build the main binary
go build -o osmmcp ./cmd/osmmcp

# Build with version information
VERSION=$(git describe --tags --always)
COMMIT=$(git rev-parse --short HEAD)
BUILD_DATE=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
go build -ldflags="-X main.buildVersion=$VERSION -X main.buildCommit=$COMMIT -X main.buildDate=$BUILD_DATE" -o osmmcp ./cmd/osmmcp

Running the Server

Stdio Transport (Default)
# Run with stdio transport for Claude Desktop integration
./osmmcp

# Run with debug logging
./osmmcp --debug
HTTP+SSE Transport (Anthropic API Integration)
# Enable HTTP+SSE dual transport for remote MCP clients
./osmmcp --enable-http --http-addr :7082

# With authentication
./osmmcp --enable-http --http-addr :7082 --http-auth-type bearer --http-auth-token your-secret

# With custom base URL for external access
./osmmcp --enable-http --http-addr :7082 --http-base-url https://your-domain.com
Monitoring and Health Checks
# Enable monitoring server (enabled by default)
./osmmcp --enable-monitoring --monitoring-addr :9090

# Disable monitoring
./osmmcp --enable-monitoring=false

# Run with both HTTP transport and monitoring
./osmmcp --enable-http --http-addr :7082 --enable-monitoring --monitoring-addr :9090
HTTP Transport Configuration
  • --enable-http: Enable HTTP+SSE transport (disabled by default)
  • --http-addr: HTTP server address (default: ":7082")
  • --http-base-url: Base URL for service discovery (auto-detected if empty)
  • --http-auth-type: Authentication type - "none", "bearer", or "basic" (default: "none")
  • --http-auth-token: Authentication token/credentials
Monitoring Configuration
  • --enable-monitoring: Enable Prometheus metrics and health endpoints (default: true)
  • --monitoring-addr: Monitoring server address (default: ":9090")

Read the full file on GitHub · 261 lines

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. 5d ago First seen · 261 lines · 2,107 tokens per session scan A 1cc19ff53584

Subscribe to this mod's changes

osmmcp CLAUDE.md is an instructions file published in the GitHub repository NERVsystems/osmmcp (28 stars, last pushed 5mo ago), licensed MIT. It adds 2,107 tokens to every session, about $0.0105 per session on Opus 5. 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.