What is dive-mcp-host CLAUDE.md?

Project-specific instructions for dive-mcp-host, a Python service that can run on its own or be started by the Dive desktop app.

Use them when installing dependencies, running the service or command-line client, testing, formatting, or changing the service's data format.

They give the coding agent the right setup, commands, testing steps, and compatibility rules for this repository.

How OpenAgentPlatform/dive-mcp-host configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OpenAgentPlatform/dive-mcp-host. 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/OpenAgentPlatform/dive-mcp-host/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/OpenAgentPlatform/dive-mcp-host

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/openagentplatform/dive-mcp-host/claude-md/github.svg)](https://agentmods.dev/instructions/openagentplatform/dive-mcp-host/claude-md)

Your own site

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

Per session 1,913 This file is loaded in full into every session.

When invoked 1,913 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	$0.01913	$0.01913
Opus 5.5	$0.00765	$0.00765
Sonnet 5.5	$0.00383	$0.00383
Haiku 4.5	$0.00191	$0.00191

Measured 2mo ago against content hash 6694065864a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dive-mcp-host 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.

Project Role

This repo is dive-mcp-host — the Python MCP host service. It is consumed two ways:

as a standalone HTTP service (dive_httpd) and CLI (dive_cli)
as the Python submodule of the Dive desktop app (Electron + Tauri), which spawns this service as a child process

Backend changes that touch the wire format must stay backwards-compatible with whatever Dive frontend is in the field. See memory/feedback_backcompat.md for the discipline.

Common Commands

# Install runtime + dev deps (uv is preferred)
uv sync --extra dev --frozen
# fallback: pip install -e ".[dev]"

# Start HTTP service on 0.0.0.0:61990
dive_httpd

# One-shot CLI chat
dive_cli "hello"
dive_cli -c CHAT_ID "follow-up"   # resume a thread

# Tests
pytest                                              # full suite
pytest tests/test_tools.py::test_mcp_server_info    # single test
pytest -m integration                               # integration only
uv run --extra dev --frozen pytest                  # without activating venv

# Lint / format (ruff is the only linter; ruff format is the formatter)
ruff check .
ruff format .

# Local Postgres for tests/dev (optional)
./scripts/run_pg.sh

# DB migrations (alembic.ini → ./dive_mcp_host/httpd/database/migrations/)
alembic upgrade head
alembic revision --autogenerate -m "<message>"

Running tests in this sandbox

Tests subprocess-spawn python3 from PATH. If running outside the project venv, prepend it explicitly so the child processes see the installed deps:

PATH="$PWD/.venv/bin:$PATH" \
PYTHONPATH=/path/to/extra/deps:$PWD \
.venv/bin/python -m pytest tests/...

Architecture

Layered structure

dive_mcp_host/
├── host/         ← core SDK (no HTTP, embeddable)
├── httpd/        ← FastAPI server wrapping the SDK
├── cli/          ← dive_cli entry point
├── models/       ← LLM provider loaders
├── skills/       ← skill (markdown-with-frontmatter) loader
├── plugins/      ← plugin discovery
├── oap_plugin/   ← OpenAgentPlatform integration
├── internal_tools/ ← built-in non-MCP tools (fetch, bash, file IO)
└── scheduler/    ← background scheduling

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.

2mo ago First seen · 184 lines · 1,913 tokens per session scan A 6694065864a7

Subscribe to this mod's changes

dive-mcp-host CLAUDE.md is an instructions file published in the GitHub repository OpenAgentPlatform/dive-mcp-host (48 stars, last pushed 3mo ago), licensed MIT. It adds 1,913 tokens to every session, about $0.0077 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.

dive-mcp-host CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dive-mcp-host CLAUDE.mdOpenAgentPlatform/dive-mcp-host	Instructions file	48	3mo ago	MIT	A	1,913	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	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

dive-mcp-host: Instructions file for Claude Code