Borrowing it
Nothing to install: this file belongs to changjonathanc/mcp-registry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/changjonathanc/mcp-registry/main/CLAUDE.mdgit clone --depth 1 https://github.com/changjonathanc/mcp-registryWrote 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.
[](https://agentmods.dev/instructions/changjonathanc/mcp-registry/claude-md)<a href="https://agentmods.dev/instructions/changjonathanc/mcp-registry/claude-md"><img src="https://agentmods.dev/badge/instructions/changjonathanc/mcp-registry/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.
<a href="https://agentmods.dev/instructions/changjonathanc/mcp-registry/claude-md"><img src="https://agentmods.dev/badge/instructions/changjonathanc/mcp-registry/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01298 | $0.01298 |
| Opus 5.5 | $0.00519 | $0.00519 |
| Sonnet 5.5 | $0.00260 | $0.00260 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
mcp-registry 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude's Reference Guide for MCP Registry
Core Architecture
- MCP Registry: Manages MCP servers, provides CLI tools, and aggregates server tools
- Server configuration: Stored in
~/.config/mcp_registry/mcp_registry_config.json(configurable viaMCP_REGISTRY_CONFIG)
Key Components
-
ServerRegistry (
compound.py)- Loads/saves server configurations from JSON
- Maps server names to
MCPServerSettingsobjects - Creates client sessions for connecting to servers
- Supports filtering to create subsets with
filter_servers()
-
MCPAggregator (
compound.py)- Namespaces tools as
server_name__tool_name - Supports temporary and persistent connections
- Handles tool listing and calling across servers
- Implements the
list_tools()andcall_tool()methods - Key entrypoint for programmatic tool calls
- Supports tool-level filtering with
tool_filterparameter
- Namespaces tools as
-
MCPConnectionManager (
connection.py)- Handles concurrent persistent connections
- Uses async context managers for proper lifecycle
- More efficient for multiple tool calls
-
CLI Commands (
cli.py,commands/*.py)- init: Create config file and import Claude Desktop settings
- add/remove/list: Manage server configurations
- serve: Run compound server with all/selected servers
- list-tools: Display tools from servers with 3 verbosity levels
- test-tool: Test tools interactively or programmatically
Core Files
src/mcp_registry/compound.py: Server registry, settings, and aggregatorsrc/mcp_registry/connection.py: Persistent connection managementsrc/mcp_registry/cli.py: Main CLI entrypointsrc/mcp_registry/commands/tools.py: Tool-related commands (list-tools, test-tool)src/mcp_registry/commands/serve.py: Server commandsrc/mcp_registry/utils/config.py: Configuration utilitiessrc/mcp_registry/utils/cli.py: CLI decorators and helpers
Important Code Patterns
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 · 157 lines · 1,298 tokens per session scan A 99cf93286756
mcp-registry CLAUDE.md is an instructions file published in the GitHub repository changjonathanc/mcp-registry (5 stars, last pushed 1y ago), licensed Apache-2.0. It adds 1,298 tokens to every session, about $0.0052 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.
mcp-registry CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-registry CLAUDE.mdchangjonathanc/mcp-registry | Instructions file | 5 | 1y ago | Apache-2.0 | A | 1,298 | 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 | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 280k | 2d ago | MIT | A | 4,325 | Codex, OpenCode |