What is counsel-mcp CLAUDE.md?

Repository instructions for Counsel MCP, a server that lets AI coding tools connect to the Counsel API using the Model Context Protocol (MCP), a standard way for AI clients to use external tools.

Building, developing, starting, or configuring Counsel MCP for clients such as Claude Desktop, Cursor, or VS Code.

It gives an AI coding agent the commands, architecture, and authentication details needed to work on or run the server.

How mercurialsolo/counsel-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mercurialsolo/counsel-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mercurialsolo/counsel-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mercurialsolo/counsel-mcp

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/instructions/mercurialsolo/counsel-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mercurialsolo/counsel-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mercurialsolo/counsel-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mercurialsolo/counsel-mcp/claude-md/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/instructions/mercurialsolo/counsel-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mercurialsolo/counsel-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 691 This file is loaded in full into every session.

When invoked 691 The same file — it is already loaded in full.

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	$0.00691	$0.00691
Opus 5.5	$0.00276	$0.00276
Sonnet 5.5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured 2mo ago against content hash cb65666cb821, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

counsel-mcp CLAUDE.md 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.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build and Development Commands

npm run build    # Compile TypeScript to dist/ and make executable
npm run dev      # Watch mode for TypeScript compilation
npm run start    # Run the MCP server (HTTP mode on port 3000)

CLI Options:

npx counsel-mcp start --port 8080 --host 0.0.0.0

Architecture

This is an MCP (Model Context Protocol) server that acts as an open-source gateway to the Counsel API. It uses HTTP transport with native MCP OAuth support, allowing MCP clients (Claude Desktop, Cursor, VSCode, etc.) to handle authentication automatically.

How It Works

MCP Client adds this server to their configuration
OAuth Flow is handled natively by the MCP client via standard endpoints
Authentication proxies to Counsel API (counsel.getmason.dev)
Tools execute against Counsel API using the authenticated user's token

Core Components

src/index.ts - Express HTTP server with MCP SDK integration:
- ProxyOAuthServerProvider - Proxies OAuth to Counsel API
- mcpAuthRouter - Exposes /authorize, /token, /register, /.well-known/*
- requireBearerAuth - Protects /mcp endpoint
- StreamableHTTPServerTransport - MCP protocol over HTTP/SSE
src/client.ts - Axios client with AsyncLocalStorage for request-scoped auth tokens
src/config.ts - Zod-validated configuration (primarily COUNSEL_API_URL)

OAuth Endpoints

The server exposes standard OAuth 2.0 endpoints that proxy to Counsel API:

GET /.well-known/oauth-authorization-server - OAuth metadata
GET /authorize - Authorization endpoint (redirects to Counsel)
POST /token - Token exchange (proxies to Counsel)
POST /register - Dynamic client registration (proxies to Counsel)

Tool System

Tools in src/tools/ export a TOOLS object with:

name, description, schema (Zod), handler

Read the full file on GitHub · 84 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 · 84 lines · 691 tokens per session scan A cb65666cb821

Subscribe to this mod's changes

counsel-mcp CLAUDE.md is an instructions file published in the GitHub repository mercurialsolo/counsel-mcp (6 stars, last pushed 10mo ago), licensed MIT. It adds 691 tokens to every session, about $0.0028 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 2026-08-31.

counsel-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
counsel-mcp CLAUDE.mdmercurialsolo/counsel-mcp	Instructions file	6	10mo ago	MIT	A	691	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	yesterday	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

counsel-mcp: Instructions file for Claude Code