One MCP, many parsers

io.github.adelaidasofiaPublished by GitHub account adelaidasofiav0.1.0Updated Oct 27, 2026

One MCP, many parsers. Routes between markitdown, Docling, and LlamaParse. Plus an interpret tool…

The publisher's own server: Parse

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Converts files and URLs to markdown through several parsers (markitdown, Docling, LlamaParse), with optional Claude interpretation and chunking.

What you can do
  • Parse a local file path or http(s) URL to markdown, letting the router pick a backend or forcing one, and see every backend attempted
  • Parse URLs directly with the same output shape
  • Parse and save the result as a markdown note in a vault folder, with frontmatter recording source, format, backend, latency and bytes
  • Parse then ask Claude over the parsed markdown to summarize or extract content, reusing cached text
  • Chunk parsed markdown into retrieval-ready pieces using doc-type-aware chunkers, and detect which doc type would be chosen
  • List installed and missing backends, and benchmark all available backends on one input
When to use it
Useful when you need to turn PDFs, Office documents, HTML or other files into markdown for an assistant, and want a free fast default with the option to escalate to OCR or layout-aware parsing for scanned, image or multi-column documents.
Requirements
Runs locally over stdio as a Python 3.13+ process (FastMCP) with markitdown installed; Docling and LlamaParse are optional extras installed separately. LlamaParse routing needs the LLAMA_CLOUD_API_KEY secret; Docling downloads model weights on first run. Network access is needed for URL parsing and for the one-time anonymous install signal.
Before you install
The vault-writing tool creates or overwrites markdown notes in your vault, so check the target folder and overwrite setting. LlamaParse sends documents to a cloud service and needs LLAMA_CLOUD_API_KEY. The README documents a one-time anonymous install ping to an external host, opt-out via MYCELIUM_NO_PING=1. Docling downloads model weights on first run.

Installation

In SourceWeft

  1. Open One MCP, many parsers in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

parse-mcp

[License] [GitHub stars] [Last commit] [Open issues] [PyPI version] [PyPI downloads] [Built by Mycelium AI]

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.

Install

Open Claude Code, paste:

/plugin marketplace add adelaidasofia/parse-mcp/plugin install parse-mcp@parse-mcp
Legacy install

Manual install (pre-plugin-marketplace). See SETUP.md for full details.

bash
pip3 install --break-system-packages -r requirements.txtpip3 install --break-system-packages 'markitdown[pdf,docx,pptx,xlsx]'

Then register the server in your client's .mcp.json:

json
{  "mcpServers": {    "parse": {      "command": "python3",      "args": ["/absolute/path/to/parse-mcp/server.py"]    }  }}

Tools

ToolWhat 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.

Backends (priority order)

  1. markitdown (default, MIT, base install). PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, EPub, ZIP. Fast, deterministic.
  2. docling (optional, pip install docling). Best for complex tables (97.9% on benchmark) + scanned PDFs. Downloads model weights on first run.
  3. llamaparse (optional, BYOK, pip install llama-cloud-services + LLAMA_CLOUD_API_KEY). Cloud, cleanest output on visually-complex PDFs.

Routing strategy

  • 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.
  • Unavailable backends are skipped (logged in the chain), never errored.

Parse-fidelity eval

The routing table above used to be a guess. tests/eval/ turns it into data: a synthetic fixture corpus (16 documents across digital PDF, scanned/image-only PDF, table-heavy, multi-column, and raster image classes) with derived ground-truth markdown, scored against each backend's output on three OmniDocBench / PubTabNet metrics — text edit distance, table TEDS (tree-edit-distance similarity), and reading-order. All scores are quality in [0, 1], higher is better.

Headline result (full table: tests/eval/parse_fidelity_matrix.md):

doc-classmarkitdown (text)docling (text)
digital_pdf0.950.97
table_heavy0.930.89
scanned_pdf0.000.87
image0.000.90
multicolumn0.351.00

markitdown is great on clean digital text and digital tables (free, fast, deterministic) but has no OCR — it scores zero on scanned PDFs and images — and it interleaves multi-column layouts. docling wins every class via OCR + layout analysis, at the cost of model-weight downloads. That is the evidence behind the format-preference chain (escalate image/scanned/multi-column to docling first).

Run it:

bash
pip install docling                      # the escalation backend under testpython tests/eval/generate_fixtures.py   # rebuild the corpus (needs fpdf2 + Pillow)make eval                                # -> parse_fidelity_matrix.{md,json}

The matrix records its provenance (backend + python versions + a fixture-set hash), so a stale result is visible — regenerate with make eval whenever a parse backend is upgraded or retuned. It also reports median latency per backend (the cost axis): the highest-fidelity backend (docling) is far slower than the default, so the router escalates to it rather than defaulting to it.

The scorer's metric tests are pure-Python and backend-free, so pytest tests/ gates them in CI with only the base (markitdown) install — a routing regression that breaks the "markitdown has no OCR" assumption fails the build.

Architecture

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.

Related MCPs

Same author, same architecture pattern (FastMCP, draft+confirm on writes, vault auto-export where applicable):

Telemetry

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:

  • Plugin name (e.g. slack-mcp)
  • Plugin version (e.g. 0.1.0)

What is NOT sent:

  • No user identifiers, names, emails, tokens, or API keys
  • No file paths, message content, or anything from your work
  • No IP address is stored after dedup processing

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.

License

MIT. See LICENSE.

Full install or team version at diazroa.com.

Source: README.md at commit ea966ce

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Parse integrations

Parse

gl.parseOfficial publisher

Lets an assistant look up how AI engines mention, recommend and cite brands, topics and questions, and manage the resulting follow-up tasks.

Streamable HTTPWeb executable
Productivity & Workflow30 toolsOct 24, 2026

PdfParse

Published by GitHub account PabloG6

Hosted MCP server that turns PDFs into structured tables, lets an assistant query the extracted records, and sets up document inbox workflows.

Streamable HTTPWeb executableAuth
Files & StorageCredential requiredOct 24, 2026

DocParse

Published by GitHub account mrsergeiluzhnov

DocParse is a remote MCP server that converts documents to Markdown and returns US financial data (SEC filings, Treasury yields, FRED macro, FX) plus small dev/

Streamable HTTPWeb executable
Files & Storage12 toolsOct 24, 2026

AILANG Parse

Published by GitHub account sunholo-data

Parses Office, PDF and image documents into structured blocks, Markdown or HTML, and converts or creates documents in nine formats.

Streamable HTTPWeb executable
Productivity & Workflow10 toolsNov 5, 2026

SemVer numbers only

Published by GitHub account sadri-dridi

A remote MCP endpoint offering 31 small utility tools: SemVer parsing, time and timezone lookups, URL and hostname inspection, HTTP status checks, and simple…

Streamable HTTPWeb executable
Web Search & Scraping31 toolsNov 2, 2026