Parse Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Parse Mcp (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
Aggregate score unchanged between these scans.
The primary manifest — the file an agent reads to learn what this artifact does.
<!-- mycelium-badges:start -->
<p> <a href="https://github.com/adelaidasofia/parse-mcp/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/github/license/adelaidasofia/parse-mcp?color=blue"></a> <a href="https://github.com/adelaidasofia/parse-mcp/stargazers"><img alt="GitHub stars" src="https://img.shields.io/github/stars/adelaidasofia/parse-mcp?color=eab308"></a> <a href="https://github.com/adelaidasofia/parse-mcp/commits/main"><img alt="Last commit" src="https://img.shields.io/github/last-commit/adelaidasofia/parse-mcp"></a> <a href="https://github.com/adelaidasofia/parse-mcp/issues"><img alt="Open issues" src="https://img.shields.io/github/issues/adelaidasofia/parse-mcp"></a> <a href="https://pypi.org/project/adelaidasofia-parse-mcp/"><img alt="PyPI version" src="https://img.shields.io/pypi/v/adelaidasofia-parse-mcp?color=blue&label=pypi"></a> <a href="https://pypi.org/project/adelaidasofia-parse-mcp/"><img alt="PyPI downloads" src="https://img.shields.io/pypi/dm/adelaidasofia-parse-mcp?color=blue&label=downloads"></a> <a href="https://myceliumai.co"><img alt="Built by Mycelium AI" src="https://img.shields.io/badge/built_by-Mycelium_AI-15B89A"></a> </p>
<!-- mycelium-badges:end -->
One MCP, many parsers. Default markitdown (free, fast, MIT). Escalate to Docling (table-heavy, scanned PDFs) or LlamaParse (cloud, BYOK) when markitdown's quality isn't enough. Plus an interpret tool that pipes parsed markdown into Claude for "summarize / extract X" so you stop juggling parsers and anthropic skills.
Open Claude Code, paste:
/plugin marketplace add adelaidasofia/parse-mcp /plugin install parse-mcp@parse-mcp
<details><summary>Legacy install</summary>
Manual install (pre-plugin-marketplace). See SETUP.md for full details.
pip3 install --break-system-packages -r requirements.txt
pip3 install --break-system-packages 'markitdown[pdf,docx,pptx,xlsx]'Then register the server in your client's .mcp.json:
{
"mcpServers": {
"parse": {
"command": "python3",
"args": ["/absolute/path/to/parse-mcp/server.py"]
}
}
}</details>
| Tool | What it does |
|---|---|
parse(source, backend?, hints?) | File path or http(s) URL to markdown. Router picks backend, falls back on empty/error. Returns markdown plus a chain of every backend attempted. |
parse_url(url, backend?) | Shortcut for HTTP(S) inputs. Same return shape as parse. |
parse_to_vault(source, vault_folder?, backend?, overwrite?) | Parse + write the result as a markdown note in the vault. Default folder: <VAULT_ROOT>/📥 Inbox/Converted/. Frontmatter records source, format, backend, latency, bytes_in. Replaces the standalone markitdown_to_vault.py shell script. |
interpret(source, instruction, backend?, model?, max_tokens?) | Parse first, then ask Claude over the parsed markdown. Cache hits reuse parsed text for free input tokens. |
list_backends() | Which backends are installed + which are missing. Diagnostic. |
benchmark(source) | Run every available backend on the same input. Compare latency + output side by side. |
chunk_text(text, doc_type?, target_tokens?, max_tokens?, min_tokens?) | Chunk parsed markdown into retrieval-ready pieces using a doc-type-aware chunker. doc_type="auto" (default) runs structural detection and picks one of paper / book / manual / qa / resume / table / default. Each chunker honors document shape (e.g., paper keeps the abstract whole; manual never merges across numbered sections; qa pairs each question with its answer). Returns chunks + the resolved doc_type. See chunkers/ package. |
detect_doc_type(text) | Diagnostic. Run structural heuristics over markdown and return the doc_type that chunk_text would pick. |
pip install docling). Best for complex tables (97.9% on benchmark) + scanned PDFs. Downloads model weights on first run.pip install llama-cloud-services + LLAMA_CLOUD_API_KEY). Cloud, cleanest output on visually-complex PDFs.parse(source) with no backend arg: router picks based on file format, falls back if backend errors or returns empty.parse(source, backend="docling"): force a specific backend, no fallback. Diagnostic mode.FastMCP v3.2.3+, stdio transport, Python 3.13+. Registered in [VAULT_ROOT]/.mcp.json. No daemons, no listeners, no model weights downloaded by default.
See SETUP.md for install + per-backend opt-in.
Same author, same architecture pattern (FastMCP, draft+confirm on writes, vault auto-export where applicable):
This plugin sends a single anonymous install signal to myceliumai.co the first time it loads in a Claude Code session on a given machine.
What is sent:
slack-mcp)0.1.0)What is NOT sent:
Why: Helps the maintainer know which plugins people actually install, so attention goes to the ones that get used.
Opt out: Set the environment variable MYCELIUM_NO_PING=1 before launching Claude Code. The hook will skip the network call entirely. Already-pinged installs leave a sentinel at ~/.mycelium/onboarded-<plugin> — delete it if you want to reset state.
MIT. See LICENSE.
Full install or team version at diazroa.com.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.