{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_22s9xm3j8jrp","handle":"mcp-docgen","url":"https://wellknown.network/agents/mcp-docgen","links":{"self":"https://wellknown.network/agents/mcp-docgen/record.json","html":"https://wellknown.network/agents/mcp-docgen","markdown":"https://wellknown.network/agents/mcp-docgen/record.md","api":"https://wellknown.network/api/v1/agents/mcp-docgen","status":"https://wellknown.network/api/v1/agents/mcp-docgen/status","claim":"https://wellknown.network/agents/mcp-docgen/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-docgen/claim.json","badge":"https://wellknown.network/agents/mcp-docgen/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-docgen/history","tools":"https://wellknown.network/api/v1/agents/mcp-docgen/tools"},"ard":{"identifier":"urn:air::server:mcp-docgen","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-docgen","summary":"Markdown-driven MCP server to create, read and edit Word (.docx), Excel (.xlsx), PowerPoint (.pptx) and PDF documents — by the Touka project.","description":"# mcp-docgen \n \nA Markdown-driven [Model Context Protocol](https://modelcontextprotocol.io) (MCP) server \nto **create, read, edit and convert** **Word (`.docx`)**, **Excel (`.xlsx`)**, \n**PowerPoint (`.pptx`)**, **PDF** and **HTML** documents. \n \nBuilt entirely on mature, permissively-licensed Python libraries \n([`python-docx`](https://github.com/python-openxml/python-docx), \n[`python-pptx`](https://github.com/scanny/python-pptx), \n[`openpyxl`](https://foss.heptapod.net/openpyxl/openpyxl), \n[`reportlab`](https://pypi.org/project/reportlab/), \n[`pypdf`](https://github.com/py-pdf/pypdf), \n[`markdown-it-py`](https://github.com/executablebooks/markdown-it-py), \n[`markdownify`](https://github.com/matthewwithanm/python-markdownify), \n[`beautifulsoup4`](https://www.crummy.com/software/BeautifulSoup/)) — no proprietary \ndependencies. **MIT licensed.** \n \n> Part of the **Touka** project: giving AI agents the ability to produce, read and edit \n> real Office documents using only open-source building blocks. \n \n## Why \n \nLLMs are great at producing Markdown. `mcp-docgen` converts Markdown to polished Office \ndocuments — and reads them back to Markdown — so an MCP-capable assistant (Claude Desktop, \nTouka, …) can run a full **read → edit → write** loop on real `.docx` / `.xlsx` / `.pptx` \n/ `.pdf` / `.html` files, and **convert** between any of them. \n \n## Install & run \n \n```bash \nuvx mcp-docgen          # once published to PyPI \n# or, from a local checkout: \nuv sync && uv run mcp-docgen \n``` \n \nThe server speaks MCP over **stdio**. \n \n## MCP client configuration \n \n```jsonc \n{ \n  \"mcpServers\": { \n    \"docgen\": { \n      \"command\": \"uvx\", \n      \"args\": [\"mcp-docgen\"], \n      \"env\": { \"MCP_DOCGEN_OUTPUT_DIR\": \"/absolute/path/to/workdir\" } \n    } \n  } \n} \n``` \n \nFrom a local checkout, swap the command for: \n \n```jsonc \n{ \"command\": \"uv\", \"args\": [\"run\", \"--directory\", \"/path/to/mcp-docgen\", \"mcp-docgen\"] } \n``` \n \n## Tools \n \n### Create (Markdown / structured data → file) \n \n| T…","publisher":{"name":"Otoha (Touka Project)","url":null},"homepage":null,"repository":null,"version":"0.8.0","license":null,"protocols":["mcp"],"tags":["mcp","model-context-protocol","docx","xlsx","pptx","word","excel","powerpoint","pdf","html","document-generation","document-reading","document-editing","document-conversion","markdown"],"pricing":null,"endpoints":[{"url":"pypi:mcp-docgen","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"documents.conversion","name":"Document Conversion","confidence":1,"provenance":"declared"},{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":1,"provenance":"declared"},{"slug":"documents.presentations","name":"Presentations","confidence":1,"provenance":"declared"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":1,"provenance":"derived"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"provenance":"derived"},{"slug":"content.writing","name":"Writing & Editing","confidence":0.656,"provenance":"derived"}],"categories":["content","dev","documents"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-docgen","registry":"pypi","observedAt":"2026-10-22T08:25:02.253Z","publishedAt":"2026-07-09T15:00:55.617542Z","latestVersion":"0.8.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-docgen","url":"https://pypi.org/project/mcp-docgen/","firstSeenAt":"2026-09-10T01:20:08.523Z","fetchedAt":"2026-10-22T08:23:42.516Z","normalizedAt":"2026-10-22T08:23:42.516Z"}]},"firstSeenAt":"2026-09-10T01:20:08.523Z","updatedAt":"2026-10-22T08:25:02.253Z"}