Instructions for managing MetaMCP, a gateway that combines several MCP servers into shared endpoints. It covers servers, namespaces, endpoints, API keys, and connection URLs for agents such as Claude or Cursor.

Use it to add MCP servers, group tools into namespaces, create endpoints, manage API keys, and retrieve the URL an agent should use.

It provides a defined way to connect and organize multiple tool servers without configuring each agent separately.

metamcp — Skill for Claude Code by felipefontoura

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.

Any agent

npx skills add felipefontoura/bento --skill metamcp

Clone the repo

git clone --depth 1 https://github.com/felipefontoura/bento

Made for: Claude Code.

Or install bento, the plugin that ships this one along with the rest of its 13 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/felipefontoura/bento/metamcp/github.svg)](https://agentmods.dev/skills/felipefontoura/bento/metamcp)

Your own site

<a href="https://agentmods.dev/skills/felipefontoura/bento/metamcp"><img src="https://agentmods.dev/badge/skills/felipefontoura/bento/metamcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/felipefontoura/bento/metamcp"><img src="https://agentmods.dev/badge/skills/felipefontoura/bento/metamcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,780 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00174	$0.01780
Opus 5	$0.00087	$0.00890
Sonnet 5	$0.00035	$0.00356
Haiku 4.5	$0.00017	$0.00178

Measured 10d ago against content hash fa93eccd3106, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

metamcp 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://$METAMCP_HOST/health" # → 200 OK when ready

plugins/bento/skills/metamcp/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You operate a MetaMCP gateway already deployed by bento. MetaMCP aggregates multiple MCP servers (stdio or HTTP/SSE) into unified public endpoints, each protected by API-key or OAuth auth. Day-2 work only — you configure servers, namespaces, endpoints, and API keys. For deploying the stack use /bento:deploy.

Docs (source of truth): https://github.com/metatool-ai/metamcp · https://docs.metamcp.com The web UI is the authoritative management surface — use it for all CRUD.

Management surface reality. MetaMCP's backend is a tRPC API (/trpc), consumed by the Next.js web UI. There is no documented public REST API with stable versioned routes. For interactive configuration, use the web UI (always safe). For automation, tRPC procedures are callable but internal and unversioned — verify schemas against the running container before scripting.

When to invoke

"add / list MCP servers" · "create a namespace / endpoint" · "create / rotate an API key"
"get the URL to plug into Claude / Cursor / my agent"
"wire MetaMCP into hermes"

For getting MetaMCP running use /bento:deploy. For AI provider keys use /bento:auth.

Discover the instance — don't hardcode

ssh "$user@$host" "jq -r '.envs.metamcp.METAMCP_HOST' \$HOME/.config/bento/state.json"

Base URL = https://<METAMCP_HOST>. The backend listens on internal port 12008. Container name (conventional in bento swarm): metamcp_*.1.*

metamcp_container() { ssh "$user@$host" "docker ps --filter name=metamcp_ -q | head -1"; }

Health probe (resolves only after DB migrations + session pool init):

curl -s "https://$METAMCP_HOST/health"   # → 200 OK when ready

Auth model

Admin UI — Better Auth sessions. First visitor self-registers as admin via https://<METAMCP_HOST> → "Create account". Session-cookie based; no seeded credentials.

MCP endpoint access — API keys (sk_mt_...). Create in the UI: Settings → API Keys. The key is shown only once — copy immediately. Use as Authorization: Bearer sk_mt_<key>.

Read the full file on GitHub · 146 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.

10d ago First seen · 146 lines · 0 tokens per session scan A fa93eccd3106

Subscribe to this mod's changes

metamcp is a skill published in the GitHub repository felipefontoura/bento (20 stars, last pushed 1mo ago), licensed MIT. It adds 174 tokens to every session and 1,780 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs Building agents automation docker-swarm portainer self-hosted server-hardening

credential-setup-with-computer-use

Guides n8n credential setup through Computer Use browser tools. Use when a user needs OAuth apps, API keys, client IDs, client secrets, or other credential values from an external service console.

n8n-io/n8n · 48 tokens

n8n-docs-assistant

Answers n8n product, setup, credential, node, hosting, API, and usage questions from current n8n docs. Load n8n-docs via loadtool before calling it (search "n8n docs" if not visible). Use when the user asks how to configure, set up, troubleshoot, or understand n8n behavior, especially credential setup questions opened…

n8n-io/n8n · 89 tokens

trigger-authoring-tasks

Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…

triggerdotdev/trigger.dev · 115 tokens

voiden

Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.

VoidenHQ/voiden · 28 tokens

debugging-executions

Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.