Borrowing it
Nothing to install: this file belongs to wisflux/docmost-local-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.
curl -O https://raw.githubusercontent.com/wisflux/docmost-local-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/wisflux/docmost-local-mcpWrote 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/wisflux/docmost-local-mcp/claude-md)<a href="https://agentmods.dev/instructions/wisflux/docmost-local-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wisflux/docmost-local-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.
<a href="https://agentmods.dev/instructions/wisflux/docmost-local-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wisflux/docmost-local-mcp/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 | $0.02174 | $0.02174 |
| Opus 5.5 | $0.00870 | $0.00870 |
| Sonnet 5.5 | $0.00435 | $0.00435 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
docmost-local-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 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for working in this repository.
Response style
-
Explain simply. Answer in plain, concise language. Avoid jargon where a plain word works; when a technical term is unavoidable, define it in one short clause.
-
Lead with the diagram or a one-line summary, then add brief supporting text — not a wall of prose.
What this is
docmost-local-mcp is a Rust, read-only MCP server that fronts a self-hosted Docmost instance for local IDE / AI tools (Cursor, Claude Desktop, etc.). It speaks MCP over stdio using rmcp 0.6, authenticates to Docmost with email/password (storing the session locally), and exposes documentation as MCP tools. It is distributed as an npx package (@wisflux/docmost-local-mcp) whose Node launcher downloads the Rust binary from GitHub Releases.
Edition 2024. The crate is both a binary and a library (docmost_local_mcp); integration tests in tests/ consume the library.
Commands
cargo build # debug build (default feature: native-webview = tao + wry)
cargo build --release # release build
cargo test # unit + integration tests (tests/ use tempfile + mock axum servers)
cargo fmt --check # format — CI runs this
cargo clippy --all-targets --all-features -- -D warnings # lint — CI fails on any warning
# Run the MCP server locally (talks MCP over stdio):
cargo run -- --base-url=https://docs.example.com
DOCMOST_BASE_URL=https://docs.example.com cargo run
# Build without the native auth window (forces browser-fallback login):
cargo build --no-default-features
--base-url(orDOCMOST_BASE_URL) selects the Docmost instance; it's optional — if absent the interactive login asks for it.DOCMOST_DISABLE_KEYRING=1skips the OS keyring and uses the encrypted-file credential fallback (used by tests).DEBUG_DOCMOST_MCP=1(ortrue) enables debug logging (viadebug::debug_log, prefix[docmost-local-mcp][ts][scope]), which goes to stderr — never stdout, which is reserved for the MCP protocol.
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 · 64 lines · 2,174 tokens per session scan A 17dc1ff4e0ca
docmost-local-mcp CLAUDE.md is an instructions file published in the GitHub repository wisflux/docmost-local-mcp (15 stars, last pushed 3mo ago), licensed MIT. It adds 2,174 tokens to every session, about $0.0087 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.
docmost-local-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docmost-local-mcp CLAUDE.mdwisflux/docmost-local-mcp | Instructions file | 15 | 3mo ago | MIT | A | 2,174 | 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 |