{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_rv958reeqvd5","handle":"doc-index-mcp","url":"https://wellknown.network/agents/doc-index-mcp","links":{"self":"https://wellknown.network/agents/doc-index-mcp/record.json","html":"https://wellknown.network/agents/doc-index-mcp","markdown":"https://wellknown.network/agents/doc-index-mcp/record.md","api":"https://wellknown.network/api/v1/agents/doc-index-mcp","status":"https://wellknown.network/api/v1/agents/doc-index-mcp/status","claim":"https://wellknown.network/agents/doc-index-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/doc-index-mcp/claim.json","badge":"https://wellknown.network/agents/doc-index-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/doc-index-mcp/history","tools":"https://wellknown.network/api/v1/agents/doc-index-mcp/tools"},"ard":{"identifier":"urn:air::server:doc-index-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"doc-index-mcp","summary":"MCP server for semantic document search with boundary-aware chunking","description":"# Doc Index MCP\n\n## What is This For?\n\nA local-first semantic search server for your documents. Index PDFs, Word docs, PowerPoints, Excel files, and text/markdown, then search them using natural language via the Model Context Protocol (MCP).\n\n- **Semantic search** - Find relevant content using natural language queries\n- **Boundary-aware chunking** - Respects document structure (chapters, sections, headers)\n- **Table extraction** - Extract tables from documents as CSV\n- **Fully local** - No external APIs, no cloud services, no Docker containers, no PyTorch\n- **Lightweight** - ONNX-based embeddings (~50MB vs ~2GB for PyTorch)\n\n## Quick Start\n\n### 1. Add to your MCP config\n\nRequires [uv](https://docs.astral.sh/uv/getting-started/installation/). If you don't have uv, see [Alternative Installation](#alternative-installation) below.\n\nAdd to `.mcp.json` in your project root (for Claude Code) or your Claude Desktop config:\n\n```json\n{\n  \"mcpServers\": {\n    \"doc-index\": {\n      \"command\": \"uvx\",\n      \"args\": [\"doc-index-mcp\"]\n    }\n  }\n}\n```\n\n### 2. Install the skill (optional)\n\nThe skill teaches the agent how to use the search tools effectively (token budgets, boundary expansion, structure-first retrieval):\n\n```bash\nuvx --from doc-index-mcp doc-index-install-skill\n```\n\nThat's it — start asking Claude to index and search your documents.\n\n<details>\n<summary>Other agents</summary>\n\n**Hermes Agent** reads skills from `~/.hermes/skills/<category>/` rather than per-project, and configures MCP servers in `~/.hermes/config.yaml`:\n\n```bash\nuvx --from doc-index-mcp doc-index-install-skill --target hermes\n```\n\n```yaml\nmcp_servers:\n  doc-index:\n    command: uvx\n    args:\n      - doc-index-mcp\n```\n\nThe installer honours `HERMES_HOME`, so non-default profiles install to the right place. Restart the Hermes session afterwards so the skill is picked up.\n\n</details>\n\n## Supported Formats\n\n| Format | Extensions | Notes |\n|--------|------------|-------|\n| Text | `.txt` | Plain text |\n| Markdo…","publisher":null,"homepage":null,"repository":null,"version":"0.2.0","license":"MIT License\n        \n        Copyright (c) 2026 Mike\n        \n …","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:doc-index-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":0.894,"provenance":"derived"},{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":0.733,"provenance":"derived"}],"categories":["data","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":"doc-index-mcp","registry":"pypi","observedAt":"2026-10-27T23:25:36.977Z","publishedAt":"2026-08-08T22:40:36.602889Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"doc-index-mcp","url":"https://pypi.org/project/doc-index-mcp/","firstSeenAt":"2026-09-09T14:31:56.874Z","fetchedAt":"2026-10-27T23:24:47.821Z","normalizedAt":"2026-10-27T23:24:47.821Z"}]},"firstSeenAt":"2026-09-09T14:31:56.874Z","updatedAt":"2026-10-27T23:25:36.977Z"}