What is cellpose_mcp CLAUDE.md?

A set of project instructions for working on cellpose-mcp, a Python server that lets AI assistants use Cellpose for cell-image segmentation. It documents the project structure, commands, and development setup.

Use it when developing or maintaining the server, running its MCP tools, installing it for AI applications, or checking changes with tests and linters.

It gives a coding agent the repository context needed to install, run, test, format, and type-check the project correctly.

How surajinacademia/cellpose_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to surajinacademia/cellpose_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/surajinacademia/cellpose_mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/surajinacademia/cellpose_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/surajinacademia/cellpose_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/surajinacademia/cellpose_mcp/claude-md)

Your own site

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

Per session 678 This file is loaded in full into every session.

When invoked 678 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	$0.00678	$0.00678
Opus 5	$0.00339	$0.00339
Sonnet 5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 8d ago against content hash 84bd7d048d6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cellpose_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 8d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 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.

Project Overview

cellpose-mcp is a Python MCP (Model Context Protocol) server that exposes Cellpose cell segmentation capabilities to AI assistants (Claude Desktop, Cursor, Claude Code). It wraps Cellpose's segmentation, restoration, and training APIs as MCP tools.

Common Commands

# Install for development
pip install -e ".[test,dev]"

# Run the MCP server
python -m cellpose_mcp
# or: cellpose-mcp

# Install MCP config for AI apps
cellpose-mcp-install cursor
cellpose-mcp-install claude-desktop

# Run tests
pytest
pytest -m "not slow"          # skip slow tests
pytest tests/test_file.py::test_name  # single test

# Lint and format
ruff check src/ tests/ --fix
ruff format src/ tests/

# Type check
mypy src/cellpose_mcp --ignore-missing-imports

Architecture

AI App (Claude/Cursor) ──MCP Protocol──▶ FastMCP Server ──▶ Tools ──▶ Cellpose

Entry flow: __main__.py → server.py (imports mcp + tools) → mcp_instance.py (FastMCP singleton) → tools.py (11 tool functions)

Key files:

src/cellpose_mcp/tools.py — All 11 MCP tool implementations (segmentation, restoration, training, utilities). This is the main file for feature work.
src/cellpose_mcp/mcp_instance.py — Single shared FastMCP instance imported by tools and server.
src/cellpose_mcp/cli/install.py — Auto-installer that writes MCP config for Cursor/Claude Desktop.

Tool registration pattern: Functions in tools.py are decorated with @mcp.tool(), then the raw callable is re-extracted via .fn so tools can also be called directly in tests:

@mcp.tool()
def segment_cells_2d(...): ...
_segment_cells_2d_tool = segment_cells_2d  # MCP-decorated version
segment_cells_2d = segment_cells_2d.fn      # raw callable

Important Details

OpenMP env vars (KMP_DUPLICATE_LIB_OK, OMP_NUM_THREADS) must be set before cellpose import. They are set in __init__.py, __main__.py, tools.py, and .mcp.json.
Cellpose v3/v4 compatibility: tools.py handles API differences in return values (3 vs 4 tuple elements) and model type parameters. Check existing patterns when modifying tools.
Diameter parameter: Value of 0 is converted to None for Cellpose's auto-estimation. Follow this convention for new tools.
Test markers: slow, integration, unit, smoke — defined in pyproject.toml.
Docstring format: numpy-style docstrings on all tool functions.

Read the full file on GitHub · 64 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.

8d ago First seen · 64 lines · 678 tokens per session scan A 84bd7d048d6b

Subscribe to this mod's changes

cellpose_mcp CLAUDE.md is an instructions file published in the GitHub repository surajinacademia/cellpose_mcp (0 stars, last pushed 21d ago), licensed BSD-3-Clause. It adds 678 tokens to every session, about $0.0034 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.

Languages Python Scientific cell-biology image-analysis-workflows

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

cellpose_mcp: Instructions file for Claude Code