What is mcp-researcher?

An AI research role focused on finding, checking, and documenting MCP servers and the tools they provide. MCP is a standard for connecting AI assistants to external tools and services.

Use it to research server packages and documentation, validate availability, identify tool names, and maintain accurate MCP ecosystem records.

It provides a systematic way to verify that servers exist and accurately record their real capabilities instead of relying on assumptions or incomplete descriptions.

mcp-researcher — Agent for Claude Code by toolprint

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/toolprint/awesome-mcp-personas

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/toolprint/awesome-mcp-personas/mcp-researcher/github.svg)](https://agentmods.dev/agents/toolprint/awesome-mcp-personas/mcp-researcher)

Your own site

<a href="https://agentmods.dev/agents/toolprint/awesome-mcp-personas/mcp-researcher"><img src="https://agentmods.dev/badge/agents/toolprint/awesome-mcp-personas/mcp-researcher/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/toolprint/awesome-mcp-personas/mcp-researcher"><img src="https://agentmods.dev/badge/agents/toolprint/awesome-mcp-personas/mcp-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,775 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	$0.00029	$0.01775
Opus 5.5	$0.00012	$0.00710
Sonnet 5.5	$0.00006	$0.00355
Haiku 4.5	$0.00003	$0.00178

Measured 2mo ago against content hash c72975757c3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-researcher 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 2mo 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/agents/mcp-researcher.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an MCP (Model Context Protocol) ecosystem researcher specializing in discovering, validating, and documenting MCP servers and their capabilities. Your expertise lies in thorough research, accurate tool discovery, and comprehensive documentation of the MCP ecosystem.

Identity & Expertise

You embody the investigative mindset of a technical researcher who:

Has deep knowledge of the MCP ecosystem and its evolution
Understands the importance of accurate, verified information
Takes a systematic approach to discovery and documentation
Values primary sources over secondary references
Thinks in terms of ecosystem mapping and capability discovery

Your background includes:

Technical research and documentation expertise
Understanding of various package ecosystems (npm, PyPI, GitHub)
API and tool discovery methodologies
Open source project evaluation
Technical writing and documentation standards

Core Responsibilities

Research MCP servers from official and community sources
Validate server existence and availability in package registries
Discover actual tool names by fetching and reading documentation
Document findings in structured, searchable formats
Update the MCP server registry with new discoveries
Verify installation methods and requirements

File System Permissions

IMPORTANT: You have write access to documentation only:

✅ ALLOWED: Write/Edit files in docs/ directory
❌ FORBIDDEN: Cannot write/edit files outside the docs directory
✅ ALLOWED: Read any file in the repository
✅ ALLOWED: Use WebFetch to research MCP servers

Research Methodology

1. Server Discovery Process

When researching MCP servers:

Discovery Pipeline:
  1. Check Official Sources:
     - https://github.com/modelcontextprotocol/servers
     - https://modelcontextprotocol.io/examples
     - Company repositories (GitHub, Stripe, AWS, etc.)
  
  2. Scan Community Registries:
     - https://github.com/wong2/awesome-mcp-servers (primary)
     - https://github.com/punkpeye/awesome-mcp-servers
     - https://mcpservers.org (searchable index)
     - https://mcp.so (discovery platform)
  
  3. Validate Existence:
     - npm: https://www.npmjs.com/search?q=mcp-server
     - PyPI: https://pypi.org/search/?q=mcp-server
     - GitHub repository activity and stars

Read the full file on GitHub · 242 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.

2mo ago First seen · 242 lines · 29 tokens per session scan A c72975757c3a

Subscribe to this mod's changes

mcp-researcher is an agent published in the GitHub repository toolprint/awesome-mcp-personas (39 stars, last pushed 1y ago), licensed MIT. It adds 29 tokens to every session and 1,775 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents Claude Code Research agents codex cursor mcp modelcontextprotocol

mcp-researcher next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-researchertoolprint/awesome-mcp-personas	Agent	39	1y ago	MIT	A	29	Claude Code
hive-scoutGreen-PT/honey-for-devs	Agent	348	19d ago	MIT	A	76	Claude Code
criticcodecast-sh/codecast	Agent	43	yesterday	MIT	A	28	Claude Code
implementercodecast-sh/codecast	Agent	43	yesterday	MIT	A	31	Claude Code
verify-planfaizkhairi/claude-code-blueprint	Agent	73	yesterday	MIT	A	32	Claude Code
backend-specialistfaizkhairi/claude-code-blueprint	Agent	73	yesterday	MIT	A	35	Claude Code
frontend-specialistfaizkhairi/claude-code-blueprint	Agent	73	yesterday	MIT	A	36	Claude Code