MCP server for semantic document search with boundary-aware chunking
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"doc-index-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Doc Index MCP ## What is This For? A 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). - **Semantic search** - Find relevant content using natural language queries - **Boundary-aware chunking** - Respects document structure (chapters, sections, headers) - **Table extraction** - Extract tables from documents as CSV - **Fully local** - No external APIs, no cloud services, no Docker containers, no PyTorch - **Lightweight** - ONNX-based embeddings (~50MB vs ~2GB for PyTorch) ## Quick Start ### 1. Add to your MCP config Requires [uv](https://docs.astral.sh/uv/getting-started/installation/). If you don't have uv, see [Alternative Installation](#alternative-installation) below. Add to `.mcp.json` in your project root (for Claude Code) or your Claude Desktop config: ```json { "mcpServers": { "doc-index": { "command": "uvx", "args": ["doc-index-mcp"] } } } ``` ### 2. Install the skill (optional) The skill teaches the agent how to use the search tools effectively (token budgets, boundary expansion, structure-first retrieval): ```bash uvx --from doc-index-mcp doc-index-install-skill ``` That's it — start asking Claude to index and search your documents. <details> <summary>Other agents</summary> **Hermes Agent** reads skills from `~/.hermes/skills/<category>/` rather than per-project, and configures MCP servers in `~/.hermes/config.yaml`: ```bash uvx --from doc-index-mcp doc-index-install-skill --target hermes ``` ```yaml mcp_servers: doc-index: command: uvx args: - doc-index-mcp ``` The installer honours `HERMES_HOME`, so non-default profiles install to the right place. Restart the Hermes session afterwards so the skill is picked up. </details> ## Supported Formats | Format | Extensions | Notes | |--------|------------|-------| | Text | `.txt` | Plain text | | Markdo…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.