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.
npx agentmods add instructions/stackloklabs/mcp-optimizer/claude-mdgit clone --depth 1 https://github.com/StacklokLabs/mcp-optimizerWhat 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 | $0.00817 | $0.00817 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
mcp-optimizer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project
The general purpose of the ToolHive MCP Optimizer is to develop a MCP server that acts as an intelligent intermediary between AI clients and multiple MCP servers. The MCP Optimizer server addresses the challenge of managing large numbers of MCP tools by providing semantic tool discovery, caching, and unified access through a single endpoint.
Technical considerations
- Use uv as package manager.
uv add <package>for adding a package.uv add <package> --devfor development packages for linting and testing - Use the taskfile for running linting and formatting
task formatfor running formatterstask lintfor running linterstask typecheckfor running typecheckerstask testfor running tests
- Use
pydanticfor validating structured data - pyproject.toml should be the central place for configuring the project, i.e. linters, typecheckers, testing, etc
- Always prefer to use native Python types over custom types, e.g. use
listinstead ofList,dictinstead ofDict, etc. - Prefer using
uv run python -c "import this"instead ofpython -c "import this". This ensures that the correct python version and environment is used.
Code Structure
- The main server code is located in
src/mcp_optimizer/server.py - The database configuration and CRUD operations are in
src/mcp_optimizer/db/ - The mcp-optimizer CLI implementation is located in
src/mcp_optimizer/cli.py
Development Workflow
- After adding or modifying code, use
task formatto automatically format the code - Then run
task lintandtask typecheckto identify and fix any remaining errors - Some formatting and linting errors can be automatically resolved by running
task format - Use
task testto run the test suite and ensure all tests pass
CLI Implementation
- Follow the pattern that every new command should group big functionality and add as parameters the inputs for that big functionality
- Prefer using logger for printing in the CLI instead of using
click.echo
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.
- 2d ago First seen · 52 lines · 817 tokens per session scan A 1eb3fbedf902
mcp-optimizer CLAUDE.md is an instructions file published in the GitHub repository StacklokLabs/mcp-optimizer (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 817 tokens to every session, about $0.0041 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.