{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_e92u6fmyj28d","handle":"tika-mcp","url":"https://wellknown.network/agents/tika-mcp","links":{"self":"https://wellknown.network/agents/tika-mcp/record.json","html":"https://wellknown.network/agents/tika-mcp","markdown":"https://wellknown.network/agents/tika-mcp/record.md","api":"https://wellknown.network/api/v1/agents/tika-mcp","status":"https://wellknown.network/api/v1/agents/tika-mcp/status","claim":"https://wellknown.network/agents/tika-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/tika-mcp/claim.json","badge":"https://wellknown.network/agents/tika-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/tika-mcp/history","tools":"https://wellknown.network/api/v1/agents/tika-mcp/tools"},"ard":{"identifier":"urn:air::server:tika-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"tika-mcp","summary":"MCP wrapper around Apache Tika for document parsing and metadata extraction.","description":"# tika-mcp\n\n`tika-mcp` is an MCP (Model Context Protocol) server that wraps [Apache Tika](https://github.com/apache/tika) and\nexposes document parsing tools over `streamable-http`.\n\nIt supports local files and optional remote URL ingestion with SSRF protections,\nplus extraction for plain text, metadata, HTML, MIME detection, and recursive\narchive content.\n\n## Features\n\n- Async direct Tika Server HTTP integration (`/tika`, `/meta`, `/detect/stream`, `/rmeta`)\n- MCP tools: `extract_text`, `extract_metadata`, `detect_mime_type`, `extract_html`, `extract_documents`\n- Local file controls (`TIKA_ALLOW_LOCAL_FILES`, `TIKA_ALLOWED_LOCAL_ROOTS`)\n- Optional remote URL ingestion with blocked private/internal targets by default\n- Bounded input and output sizes with clear tool-facing errors\n- Optional bearer-token protection for exposed MCP HTTP deployments\n\n## Requirements\n\n- Python 3.11+\n- Apache Tika Server reachable at `TIKA_URL` (default `http://localhost:9998`)\n\n## Installation\n\n```bash\npip install tika-mcp\n```\n\nOr from source:\n\n```bash\npip install .\n```\n\n## Quick Start\n\n1. Install tika-mcp:\n\n   ```bash\n   pip install tika-mcp\n   ```\n\n2. Start Apache Tika Server:\n\n   ```bash\n   docker run --rm -p 9998:9998 apache/tika:3.3.1.0\n   ```\n\n3. Start tika-mcp:\n\n   ```bash\n   export TIKA_URL=http://localhost:9998\n   tika-mcp\n   ```\n\n   It now listens at `http://127.0.0.1:8000/mcp` (transport: `streamable-http`).\n\n## Tools\n\nEvery tool takes a single argument, `source` - a local file path, or an `http(s)://`\nURL (remote URLs must be enabled). All tools are read-only.\n\n| Tool | What it does |\n|---|---|\n| `extract_text` | Extract plain text from a document (PDF, Office, HTML, and other Tika-supported formats). |\n| `extract_metadata` | Return document metadata (author, title, content type, page count, …) without the body text. |\n| `detect_mime_type` | Detect the file's MIME/content type from its bytes, without full parsing. |\n| `extract_html` | Extract structured XHTML with headings, t…","publisher":{"name":"Edgaras","url":null},"homepage":"https://github.com/Edgaras0x4E/tika-MCP","repository":"https://github.com/Edgaras0x4E/tika-MCP","version":"0.1.1","license":null,"protocols":["mcp"],"tags":["apache-tika","document-parsing","mcp","metadata-extraction","model-context-protocol","text-extraction","tika"],"pricing":null,"endpoints":[{"url":"pypi:tika-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"derived"}],"categories":["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":"tika-mcp","registry":"pypi","observedAt":"2026-10-29T00:27:01.993Z","publishedAt":"2026-07-04T22:03:36.402243Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"tika-mcp","url":"https://pypi.org/project/tika-mcp/","firstSeenAt":"2026-09-10T14:22:27.921Z","fetchedAt":"2026-10-29T00:25:25.652Z","normalizedAt":"2026-10-29T00:25:25.652Z"}]},"firstSeenAt":"2026-09-10T14:22:27.921Z","updatedAt":"2026-10-29T00:27:01.993Z"}