Dewey
Enables fetching the full Markdown content of document sections from Dewey collections for research and documentation purposes.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
@meetdewey/mcp
MCP server for Dewey — search and research your document collections from Claude, Cursor, and any MCP-compatible agent. See the full API reference for details.
Installation
Add to your claude_desktop_config.json (or equivalent MCP client config):
{
"mcpServers": {
"dewey": {
"command": "/bin/sh",
"args": ["-lc", "npx -y @meetdewey/mcp"],
"env": {
"DEWEY_API_KEY": "dwy_live_...",
"DEWEY_COLLECTION_ID": "..."
}
}
}
}Note for Windows users: replace
"command": "/bin/sh"and"args": ["-lc", "npx -y @meetdewey/mcp"]with"command": "npx"and"args": ["-y", "@meetdewey/mcp"]— the login-shell wrapper is only needed on macOS/Linux to pick up Homebrew and nvm PATH entries that Claude Desktop doesn't inherit.
Related MCP server: linked-docs
Environment variables
Variable | Required | Description |
| Yes | Your Dewey project API key |
| No | Default collection ID. When set, tools that accept |
| No | Override the API base URL (default: |
Available tools
Search & research
Tool | Description |
| List all collections in the project, including description and research instructions when set |
| Hybrid semantic + keyword search over chunk content |
| Lightweight search over section titles and summaries |
| Agentic research query with configurable depth — returns a grounded, cited answer |
| Fetch the full Markdown content of a section by ID |
Document management
Tool | Description |
| List documents in a collection with their processing status |
| List all sections in a document (table of contents with heading levels and IDs) |
| Fetch the full converted Markdown content of a document |
| Retry a failed document — clears error state and re-queues processing |
| Permanently delete a document and all its derived data |
Claims & contradictions
Tool | Description |
| List extracted factual claims from a collection or specific document, filterable by importance (1–5) |
| List detected contradictions — clusters of conflicting claims with explanations and suggested resolutions |
| Trigger an async contradiction detection run across all claims in a collection |
| Get the status and stats of the latest contradiction detection run (use to poll after |
| Apply a resolution instruction to a contradiction or dismiss it |
Deduplication
Tool | Description |
| Trigger an async deduplication run — identifies near-duplicate documents by measuring shared content across chunks and marks one per cluster as canonical |
| Get the status and stats of the latest deduplication run (use to poll after |
| List near-duplicate groups with canonical + members and coverage percentages |
| Promote a different member to canonical; old canonical becomes near_duplicate |
| Disband a group; former members rejoin retrieval as distinct documents |
Non-canonical documents are excluded from retrieval and contradiction detection. Requires enableDeduplication: true on the collection (set via dewey_update_collection or the Dewey dashboard).
Collection settings
Tool | Description |
| Get document count, storage, section/chunk/claim counts, and processing status breakdown |
| Update collection name, description, research instructions, visibility, and feature flags |
| Re-run AI section summarization across all documents (e.g. after changing the LLM model) |
| Re-run AI captioning for all images and tables across all documents |
| Permanently delete a collection and all its data |
Research instructions
Collections can have natural-language instructions that are automatically injected into the research system prompt — for example, noting units, preferred sources, or how to handle missing information. They can be set in the Dewey dashboard, via the API, or directly through dewey_update_collection. When dewey_resolve_contradiction is used to apply a resolution, the suggested instruction is also appended here automatically.
Tool usage pattern
A typical read-only research workflow:
dewey_list_collections— discover available collections and understand their purposedewey_scan_sections— quickly explore document structure to identify relevant sectionsdewey_get_section— load full content of a specific sectiondewey_search— retrieve the most relevant chunks for a focused questiondewey_research— run a full agentic research query for questions that need multi-step reasoning
For deeper analysis and curation:
dewey_get_collection_stats— assess how much content has been processeddewey_list_claims— surface the most important facts across documentsdewey_list_contradictions— identify where documents disagreedewey_resolve_contradiction— apply or dismiss each contradiction, updating collection instructions automatically
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Search and inspect source-pinned agent skills, plugins and tools through a free public MCP.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Agent-driven search: build, import, tune, search, and score result quality — all over MCP.
Search and manage your team's knowledge from MCP clients.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.4-
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to intelligently search and reference documentation using hybrid semantic + keyword search via MCP protocol.-
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to query and manage a document knowledge base via MCP, with RAG-powered search and grounded answers with citations.MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP hosts to query locally indexed notes, docs, chat logs, and other files via hybrid vector/BM25 retrieval with section-level citations. Exposes tools, resources, and prompts for searching and asking over the indexed content.-