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.
npx agentmods add instructions/arthurkatcher/meta-mcp-manager/agents-mdgit clone --depth 1 https://github.com/arthurkatcher/meta-mcp-managerWrote 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.
[](https://agentmods.dev/instructions/arthurkatcher/meta-mcp-manager/agents-md)<a href="https://agentmods.dev/instructions/arthurkatcher/meta-mcp-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/arthurkatcher/meta-mcp-manager/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01586 | $0.01586 |
| Opus 5 | $0.00793 | $0.00793 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
meta-mcp-manager AGENTS.md scanned grade A with 1 finding 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.
Reads MCP configurationlowAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
2. **Config vs runtime** — `mcp.json` = how to connect; SQLite = catalog/health/activity/tokens. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Meta MCP Manager
Instructions for coding agents working in this repository.
Project
Meta MCP Manager (meta-manager) is a self-hosted control plane that federates many upstream MCP servers (stdio + Streamable HTTP) behind one retrieval-first MCP endpoint.
Clients (Cursor, Claude, ChatGPT, Grok, …) connect once and use a small fixed meta-tool surface instead of hundreds of upstream schemas:
search_tools → get_tool_schema → call_tool
list_servers · list_tools · stats
manage_servers · manage_auth (admin)
- Package:
src/meta_manager/, CLI entrypointmeta - Version:
0.1.0(MIT) — public OSS: https://github.com/arthurkatcher/meta-mcp-manager - Runtime: Python 3.11+, single-process SQLite, warm upstream pool
- Audience: single-operator / small-team self-host today; multi-tenant SaaS is roadmap, not current scope
Orchestrator
Grok (xAI) is the primary orchestrator for this codebase in Arthur’s workspace:
- Owns end-to-end implementation, hardening, tests, Docker/OSS packaging, and local runbooks.
- Prefers small, reviewable changes that match existing ADRs over greenfield rewrites.
- When multi-step work is needed, may spawn specialized subagents (explore / plan / review) but remains accountable for the final result and for not breaking the security model.
- Does not treat “demo defaults” as production: public bind, weak keys, open DCR, and plaintext secrets are defects to fix or document, not features to expand.
Other agents (Claude Code, Cursor, CI bots) should follow this file and defer to the same ADRs.
Architecture (do not invent a second design)
| Layer | Path | Role |
|---|---|---|
| Config | config/ |
Cursor-compatible mcp.json; keep ${env:VAR} templates on disk; interpolate at runtime only |
| Runtime | runtime/ |
Warm pool; stdio serialize (ADR-003); HTTP concurrent after exclusive reconnect; SSRF; envFile |
| Catalog | catalog/ |
SQLite servers / tools + BM25 index |
| Edge | edge/ |
FastMCP meta-tools, auth context, rate limits, security headers / CSP |
| OAuth | oauth/ |
Outbound vault (Fernet) + inbound AS (PKCE, DCR, hashed tokens) |
| Audit | audit/ |
Meta-tool activity → SQLite activity (+ optional JSONL mirror) |
| Storage | storage/ |
One product DB: {META_DATA_DIR}/meta.db (schema versioned) |
| Admin | admin/ |
manage_servers / manage_auth service layer |
| Brand | brand/ |
Consent / landing pages, logos |
| CLI | main.py |
meta serve, meta backup, … |
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.
- 4d ago First seen · 125 lines · 1,586 tokens per session scan A ca224d543407
meta-mcp-manager AGENTS.md is an instructions file published in the GitHub repository arthurkatcher/meta-mcp-manager (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,586 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it A with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.