One MCP, many parsers

io.github.adelaidasofia由 GitHub 账号 adelaidasofia 发布v0.1.0更新于 Oct 27, 2026

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

发布方自己的服务：Parse

已验证STDIO仅桌面文件与存储知识与记忆

概览

AI 生成的概览

通过 markitdown、Docling、LlamaParse 等多种解析器把文件和网址转成 Markdown，并可让 Claude 解读或切分结果。

可以做什么
  • 把本地文件路径或 http(s) 网址解析为 Markdown，可由路由器选择后端或强制指定，并返回尝试过的后端链
  • 直接解析网址，返回结构与通用解析一致
  • 解析后把结果写成 vault 中的 Markdown 笔记，frontmatter 记录来源、格式、后端、耗时和字节数
  • 先解析再让 Claude 基于解析出的 Markdown 做摘要或抽取，命中缓存时复用已解析文本
  • 按文档类型感知的切分器把 Markdown 切成适合检索的片段，并检测会选用哪种文档类型
  • 列出已安装与缺失的后端，并对同一输入横向对比各可用后端的耗时与输出
适用场景
适合需要把 PDF、Office 文档、HTML 等转成 Markdown 供助手使用时；默认免费快速，遇到扫描件、图片或多栏排版可升级到带 OCR 与版面分析的后端。
运行要求
以 stdio 在本地运行，需要 Python 3.13+（FastMCP）并安装 markitdown；Docling 与 LlamaParse 为可选后端，需另行安装。使用 LlamaParse 需提供 LLAMA_CLOUD_API_KEY 密钥；Docling 首次运行会下载模型权重。解析网址和一次性匿名安装信号需要联网。
安装前请注意
写入 vault 的工具会在 vault 中创建或覆盖 Markdown 笔记，使用前确认目标文件夹与覆盖选项。LlamaParse 会把文档发送到云端服务，并需要 LLAMA_CLOUD_API_KEY。README 说明首次加载会向外部主机发送一次匿名安装信号，可用 MYCELIUM_NO_PING=1 关闭。Docling 首次运行会下载模型权重。

安装

在 SourceWeft 中

  1. 打开 控制台中的 One MCP, many parsers，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

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.

来源：README.md，提交 ea966ce

工具

0
SourceWeft 尚未在沙箱中启动过该软件包，因此其工具未知。

版本历史

1
  1. v0.1.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Parse 集成

Parse

gl.parse官方发布者

让助手查询 AI 引擎如何提及、推荐和引用品牌、主题与问题，并管理由此产生的跟进任务。

Streamable HTTP可网页运行
效率与工作流30 个工具Oct 24, 2026

PdfParse

由 GitHub 账号 PabloG6 发布

托管型 MCP 服务器，可将 PDF 转为结构化表格、让助手查询提取出的记录，并配置文档收件箱工作流。

Streamable HTTP可网页运行鉴权
文件与存储需要凭据Oct 24, 2026

DocParse

由 GitHub 账号 mrsergeiluzhnov 发布

DocParse 是一个远程 MCP 服务器，可将文档转换为 Markdown，并提供美国金融数据（SEC 文件、国债收益率、FRED 宏观、汇率）及若干开发小工具。

Streamable HTTP可网页运行
文件与存储12 个工具Oct 24, 2026

AILANG Parse

由 GitHub 账号 sunholo-data 发布

把 Office、PDF 和图片文档解析为结构化块、Markdown 或 HTML，并可在九种格式间转换或新建文档。

Streamable HTTP可网页运行
效率与工作流10 个工具Nov 5, 2026

SemVer numbers only

由 GitHub 账号 sadri-dridi 发布

一个远程 MCP 端点，提供 31 个小型工具：SemVer 解析、时间与时区查询、URL 与主机名检查、HTTP 状态检查以及简单的格式校验。

Streamable HTTP可网页运行
网页搜索与抓取31 个工具Nov 2, 2026