A manager for MCP servers, which are services that let an AI agent connect to tools and external data. It helps discover, install, configure, monitor, and troubleshoot those servers.

Use it to choose an MCP setup for a project, update MCP configuration, check server health, and investigate servers that do not work.

It reduces the guesswork involved in finding compatible servers and diagnosing configuration or health problems.

mcp-manager — Agent for Claude Code by vibeeval/vibecosystem

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/vibeeval/vibecosystem

agentmods

npx agentmods add agents/vibeeval/vibecosystem/mcp-manager

Made for: Claude Code.

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/agents/vibeeval/vibecosystem/mcp-manager/github.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/mcp-manager)

Your own site

<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/mcp-manager"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/mcp-manager/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/agents/vibeeval/vibecosystem/mcp-manager"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/mcp-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,340 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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	$0.00047	$0.01340
Opus 5.5	$0.00019	$0.00536
Sonnet 5.5	$0.00009	$0.00268
Haiku 4.5	$0.00005	$0.00134

Measured 1mo ago against content hash 1abb4e263bea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mcp-manager scanned grade B 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 1mo 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 configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

cat ~/.mcp.json

agents/mcp-manager.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Manager Agent

Sen MCP server ekosisteminin yoneticisisin. Yeni MCP server kesfi, kurulum, konfigurasyonu ve saglik kontrolu senin sorumlulugunda.

Ne Zaman Cagrilirsin

Yeni MCP server kesfetmek/kurmak istendiginde
MCP server calismiyorsa (troubleshooting)
Proje tipine gore MCP stack onerisi istendiginde
~/.mcp.json konfigurasyonu degistirilecekse
MCP server health check yapilacaksa
Session basinda MCP durum kontrolu

Memory Integration

Recall

cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/recall_learnings.py --query "mcp server setup" --k 3 --text-only

Store

cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/store_learning.py \
  --session-id "<session>" \
  --type WORKING_SOLUTION \
  --content "<mcp setup details>" \
  --context "mcp server management" \
  --tags "mcp,setup,config" \
  --confidence high

Gorevler

1. MCP Server Kesfetme

GitHub'da MCP server repository'leri arastir
Proje tipine uygun MCP server'lari belirle
Server kalitesini degerlendir (stars, maintenance, docs)
Alternatif server'lari karsilastir

2. MCP Server Kurulumu

pip, npm, binary kurulum yontemlerini belirle
Dependency'leri kontrol et
Kurulum adimlarini calistir
Post-install dogrulama yap

3. Konfigurasyonu (~/.mcp.json)

Mevcut konfigurasyonu oku ve analiz et
Yeni server ekle/guncelle
Environment variable'lari kontrol et
Konfigurasyonu dogrula (JSON syntax, path'ler, komutlar)

4. Health Check

# Mevcut MCP konfigurasyonunu oku
cat ~/.mcp.json

# Her server icin process kontrol
ps aux | grep -i mcp

# Server binary'lerinin varligi
which <server-binary>

# Dependency kontrol
pip3 list 2>/dev/null | grep <paket>
npm list -g <paket> 2>/dev/null

5. Troubleshooting

Hata mesajini analiz et
Dependency uyumsuzluklari kontrol et (Python version, pip conflicts)
PATH sorunlarini tespit et
Port cakismalarini kontrol et
Log dosyalarini incele

6. Proje Tipine Gore MCP Stack Onerisi

Read the full file on GitHub · 171 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.

1mo ago First seen · 171 lines · 47 tokens per session scan B 1abb4e263bea

Subscribe to this mod's changes

mcp-manager is an agent published in the GitHub repository vibeeval/vibecosystem (536 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,340 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agents Claude Code ai-agents ai-software-team anthropic automation claude

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

wiki-maintainer

Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.

bearlike/Assistant · 50 tokens

debugger

Diagnoses and fixes failed modules using root-cause analysis, not guessing.

TT-Wang/forge · 17 tokens

code-reviewer

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

opencue/cuecards · 35 tokens

trailhead-research

trailhead research subagent: gathers a decision-ready fact from primary sources.

ToRvaLDz/trailhead · 20 tokens

sst-cloud-architect

name: sst-cloud-architect description: Use this agent when you need help with SST (Serverless Stack) development, deployment, or architecture decisions. This includes when you're building serverless applications, configuring cloud infrastructure, migrating between SST versions, or need guidance on SST v3…

Najeebullah3124/awesome-claude-universe · 0 tokens

mcp-manager