A command for finding Model Context Protocol (MCP) servers, which let an AI coding agent connect to outside tools and services, from a catalogue of more than 2,425 servers.

Use it to find an MCP server, then view its repository link, installation command, domain tags, description, and ready-to-copy configuration.

It avoids manually searching a large reference file and helps narrow results by keyword, name, or subject area.

mcp-search — Command for Claude Code by mahmoud20138

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.

Clone the repo

git clone --depth 1 https://github.com/mahmoud20138/mcp-lookup

Made for: Claude Code.

Or install awesome-mcp-lookup, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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/commands/mahmoud20138/mcp-lookup/mcp-search/github.svg)](https://agentmods.dev/commands/mahmoud20138/mcp-lookup/mcp-search)

Your own site

<a href="https://agentmods.dev/commands/mahmoud20138/mcp-lookup/mcp-search"><img src="https://agentmods.dev/badge/commands/mahmoud20138/mcp-lookup/mcp-search/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/commands/mahmoud20138/mcp-lookup/mcp-search"><img src="https://agentmods.dev/badge/commands/mahmoud20138/mcp-lookup/mcp-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 423 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00014	$0.00423
Opus 5	$0.00007	$0.00211
Sonnet 5	$0.00003	$0.00085
Haiku 4.5	$0.00001	$0.00042

Measured 10d ago against content hash 62712774ba31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-search 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 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.

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.

commands/mcp-search.md · 54 lines

What it actually says

/mcp-search

Search 2425+ MCP servers and get ready-to-use configs.

Arguments

The user invoked this command with: $ARGUMENTS

Instructions (LAZY LOAD — never read the full file)

Parse the user's search query from $ARGUMENTS
Use Grep on skills/mcp-lookup/references/mcp-servers-lookup.md — NEVER read the full file (1.1MB)
Search using Grep for the query terms
If --domain is specified, filter to that domain section only
Present the results in a clean format

Output Format

For each match, show:

Server name with GitHub link
Install command
Domain tags
Description
Config JSON (ready to copy into mcpServers)

If No Results

Suggest related domains from the catalog
Offer to browse a specific domain
Suggest alternative search terms

If Too Many Results

Show the top 10 most relevant matches
Suggest narrowing with --domain
Group results by domain

Performance Rules

NEVER read the full reference file — always use Grep
Limit output: Max 10 results per search
Suggest narrowing if >10 matches

Available Domains

AI, Analytics, Web, Search, Finance, Design, Security, Productivity, Files, Geo, Knowledge, Database, HR, Automation, DevOps, Ecommerce, Blockchain, Media, Communication, Cloud, Science, Testing, Translation, Government, Networking, Legal, Social, ERP, News, Audio, Gaming, Travel, Healthcare, IoT, Weather, Education, Caching, Utility, Messaging, Food, CRM, Fitness, CMS

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 · 54 lines · 14 tokens per session scan A 62712774ba31

Subscribe to this mod's changes

mcp-search is a command published in the GitHub repository mahmoud20138/mcp-lookup (2 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 423 once invoked, about $0.0001 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 2026-08-31.

Building agents ai mcp model-context-protocol tools

data-mesh-contract

Create federated data product contracts for mesh architectures with SLAs, governance, and interoperability guarantees (project).

tractorjuice/arckit-claude · 21 tokens

audit-web

A command for requesting a website security assessment through an MCP tool, a way for an agent to call an external service. It requires proof of permission before any network checks.

ck3938700-ship-it/anjian-agent · 0 tokens

atrs

Generate Algorithmic Transparency Recording Standard (ATRS) record for AI/algorithmic tools.

tractorjuice/arckit-claude · 17 tokens

fr-rgpd

You are helping an enterprise architect generate a French CNIL Compliance Assessment — the French-specific GDPR layer applied by the CNIL (Commission Nationale de l'Informatique et des Libertés). Run this after /arckit-eu:eu-rgpd to add French obligations that go beyond the EU GDPR baseline.

tractorjuice/arckit-claude · 34 tokens

servicenow

Create comprehensive ServiceNow service design with CMDB, SLAs, incident management, and change control.

tractorjuice/arckit-claude · 19 tokens

eval

Legacy slash-entry shim for the eval-harness skill. Prefer the skill directly.

yihefeikong-rgb/ai-plc-integration-public · 16 tokens