configure-mcp-server: Instructions file for Claude Code

CLAUDE.md

configure-mcp-server CLAUDE.md is an instructions file for Claude Code from gleanwork/configure-mcp-server. It costs 1,956 tokens per session, scanned A, original, MIT.

Repository instructions for a command-line tool that connects MCP clients to Glean's MCP servers. MCP is a standard way for AI tools to connect to external services; the instructions cover building, testing, linting, and formatting.

In plain words
What is it for?
Building the TypeScript package, running Vitest tests, watching changes, linting, type-checking, and formatting.
Why use it?
It gives coding agents the project-specific commands and checks needed to change the repository consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is gleanwork/configure-mcp-server's own configuration. It tells Claude Code how to work on configure-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything configure-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gleanwork/configure-mcp-server. 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/gleanwork/configure-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/gleanwork/configure-mcp-server

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.

agentmods badge for configure-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gleanwork/configure-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/gleanwork/configure-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gleanwork/configure-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gleanwork/configure-mcp-server/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.

agentmods 80×15 button for configure-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gleanwork/configure-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gleanwork/configure-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,956 This file is loaded in full into every session.
When invoked 1,956 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01956 $0.01956
Opus 5.5 $0.00782 $0.00782
Sonnet 5.5 $0.00391 $0.00391
Haiku 4.5 $0.00196 $0.00196

Measured 2mo ago against content hash d85114b0a576, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

configure-mcp-server 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 · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 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.

Overview

This is a CLI tool that configures MCP (Model Context Protocol) clients to connect to Glean's MCP servers. The package is published as @gleanwork/configure-mcp-server on npm and supports both local MCP servers (stdio transport) and remote MCP servers (HTTP transport with OAuth/DCR or bearer tokens).

Development Commands

Building

npm run build              # Clean build directory, compile TypeScript, and copy templates
npm run watch             # Watch mode for TypeScript compilation

The build process:

  1. Removes the build/ directory
  2. Compiles TypeScript from src/ to build/
  3. Copies markdown templates from src/init/templates/markdown/ to build/init/templates/markdown/

Testing

npm test                  # Run tests once with Vitest
npm run test:watch        # Run tests in watch mode
npm run test:all          # Run linting, type checking, and tests

Tests are located in src/test/**/*.test.ts and use Vitest.

Linting and Formatting

npm run lint              # Run all linters (ESLint, package.json, TypeScript)
npm run lint:eslint       # Run ESLint on TypeScript files (with --fix)
npm run lint:ts           # TypeScript type checking (noEmit)
npm run format            # Format all files with Prettier

Running Locally

npm run go -- [command]   # Run the CLI using ts-node without building
node build/index.js [command]  # Run the built CLI

Single Test Execution

To run a single test file:

npm test -- src/test/configure.test.ts

Architecture

Three Main Commands

  1. local - Configures local MCP server (stdio transport)

    • Requires: --client, --token, --instance (or --env)
    • Uses @gleanwork/local-mcp-server package
  2. remote - Configures remote MCP server (HTTP transport)

    • Requires: --client, --url
    • Optional: --token (if not provided, uses OAuth with Dynamic Client Registration)
    • Uses mcp-remote package as a proxy

Read the full file on GitHub · 184 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.

  1. 2mo ago First seen · 184 lines · 1,956 tokens per session scan A d85114b0a576

Subscribe to this mod's changes

configure-mcp-server CLAUDE.md is an instructions file published in the GitHub repository gleanwork/configure-mcp-server (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,956 tokens to every session, about $0.0078 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.

Related

configure-mcp-server CLAUDE.md compared with instructions from other repositories

configure-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
configure-mcp-server CLAUDE.mdgleanwork/configure-mcp-serverInstructions file31mo agoMITA1,956Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot