What is mcp-coroot CLAUDE.md?

Instructions for setting up MCP Coroot with Claude Desktop. MCP is a way for an AI assistant to connect to outside tools or services.

Use it to configure the Coroot server in Claude Desktop, including setup with the published package, single sign-on or multi-factor login, and local development.

It gathers setup rules, testing conventions, and configuration guidance in one place so the server can be installed and maintained consistently.

How jamesbrink/mcp-coroot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jamesbrink/mcp-coroot. 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/jamesbrink/mcp-coroot/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jamesbrink/mcp-coroot

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

Your own site

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

Per session 1,901 This file is loaded in full into every session.

When invoked 1,901 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	$0.01901	$0.01901
Opus 5.5	$0.00760	$0.00760
Sonnet 5.5	$0.00380	$0.00380
Haiku 4.5	$0.00190	$0.00190

Measured 1mo ago against content hash 80218b1504ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-coroot 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 1mo 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 · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Internal notes for working on this repository.

Documentation policy

This project keeps exactly two prose documents: README.md (public) and CLAUDE.md (this file). LICENSE and CHANGELOG.md are also allowed. Do not add other markdown files; fold new documentation into one of these.

Testing standards

Test files are named test_<module>.py and mirror the module they cover.
Never use suffixes like test_final_*.py, test_new_*.py or test_all_remaining_*.py. Consolidate into the existing file instead.
Tests run against a scripted fake Coroot (tests/conftest.py), never a live instance and never the network.

Layout

src/mcp_coroot/
  config.py            Settings, read from the environment once at startup
  cli.py               Argument parsing, logging to stderr, transport selection
  client/
    base.py            Pooled httpx2 transport, lazy login, body decoding
    errors.py          Exception types mapped from Coroot's status codes
    ids.py             ApplicationId parsing and path-segment encoding
    timerange.py       Relative, epoch and ISO time parsing
    accounts.py projects.py overview.py applications.py incidents.py
    dashboards.py configuration.py metrics.py
    client.py          CorootClient, composing the above
  server/
    app.py             build_server, lifespan, annotation constants
    state.py           AppState, project resolution, StateHolder
    errors.py          guard decorator turning client errors into ToolError
    compact.py         Chart, flame graph and budget reduction
    instructions.py    The instructions string sent to clients
    resources.py       prompts.py
    tools/             One module per domain, registered by register_all

Architecture decisions

SDK. The official mcp 2.x SDK (mcp.server.mcpserver.MCPServer), not jlowin fastmcp. It ships the same day as the spec revisions it implements, masks unexpected exceptions instead of leaking them to the model, and pre-parses JSON strings for list and object parameters, which removes the string-coercion workarounds 0.1.x carried. Note that mcp.server.fastmcp no longer exists in mcp 2.x, and that fastmcp>=4 depends on mcp>=2 itself.

Read the full file on GitHub · 155 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.

1mo ago Changed · -95 lines · +132 tokens per session 80218b1504ec
2mo ago First seen · 250 lines · 1,769 tokens per session scan A 536ffb2c8fc4

Subscribe to this mod's changes

mcp-coroot CLAUDE.md is an instructions file published in the GitHub repository jamesbrink/mcp-coroot (16 stars, last pushed 1mo ago), licensed MIT. It adds 1,901 tokens to every session, about $0.0076 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.

apm claude-desktop coroot mcp metrics model-context-protocol

mcp-coroot CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-coroot CLAUDE.mdjamesbrink/mcp-coroot	Instructions file	16	1mo ago	MIT	A	1,901	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-coroot: Instructions file for Claude Code