
Dewey
Brings Dewey's document intelligence platform into any MCP client with a complete toolkit for search, research, and content curation. You get hybrid semantic search, agentic research queries with citations, section scanning, and full document management. The more interesting features include claim extraction with importance scoring, automatic contradiction detection across your corpus, and near-duplicate grouping that can exclude redundant documents from retrieval. Collections support custom research instructions that get injected into the system prompt, and contradiction resolutions can update those instructions automatically. Useful when you're working with large document collections that need more than basic RAG, especially if you're chasing down conflicting information or trying to surface high-signal facts from hundreds of pages.
- tools
- 25
- auth
- Secret needed
- transport
- STDIO, HTTP
- env vars
- 3
- last updated
- Apr 26, 2026
Tools
25 toolsPublic tool metadata for what this MCP can expose to an agent.
dewey_list_collectionsList all collections in the project, including description and research instructions when set
List all collections in the project, including description and research instructions when set
No parameter schema in public metadata yet.
dewey_searchHybrid semantic + keyword search over chunk content
Hybrid semantic + keyword search over chunk content
No parameter schema in public metadata yet.
dewey_scan_sectionsLightweight search over section titles and summaries
Lightweight search over section titles and summaries
No parameter schema in public metadata yet.
dewey_researchAgentic research query with configurable depth — returns a grounded, cited answer
Agentic research query with configurable depth — returns a grounded, cited answer
No parameter schema in public metadata yet.
dewey_get_sectionFetch the full Markdown content of a section by ID
Fetch the full Markdown content of a section by ID
No parameter schema in public metadata yet.
dewey_list_documentsList documents in a collection with their processing status
List documents in a collection with their processing status
No parameter schema in public metadata yet.
dewey_get_document_sectionsList all sections in a document (table of contents with heading levels and IDs)
List all sections in a document (table of contents with heading levels and IDs)
No parameter schema in public metadata yet.
dewey_get_document_markdownFetch the full converted Markdown content of a document
Fetch the full converted Markdown content of a document
No parameter schema in public metadata yet.
dewey_retry_documentRetry a failed document — clears error state and re-queues processing
Retry a failed document — clears error state and re-queues processing
No parameter schema in public metadata yet.
dewey_delete_documentPermanently delete a document and all its derived data
Permanently delete a document and all its derived data
No parameter schema in public metadata yet.
dewey_list_claimsList extracted factual claims from a collection or specific document, filterable by importance (1–5)
List extracted factual claims from a collection or specific document, filterable by importance (1–5)
No parameter schema in public metadata yet.
dewey_list_contradictionsList detected contradictions — clusters of conflicting claims with explanations and suggested resolutions
List detected contradictions — clusters of conflicting claims with explanations and suggested resolutions
No parameter schema in public metadata yet.
dewey_detect_contradictionsTrigger an async contradiction detection run across all claims in a collection
Trigger an async contradiction detection run across all claims in a collection
No parameter schema in public metadata yet.
dewey_get_contradiction_runGet the status and stats of the latest contradiction detection run (use to poll after `dewey_detect_contradictions`)
Get the status and stats of the latest contradiction detection run (use to poll after `dewey_detect_contradictions`)
No parameter schema in public metadata yet.
dewey_resolve_contradictionApply a resolution instruction to a contradiction or dismiss it
Apply a resolution instruction to a contradiction or dismiss it
No parameter schema in public metadata yet.
dewey_detect_duplicatesTrigger an async deduplication run — identifies near-duplicate documents by measuring shared content across chunks and marks one per cluster as canonical
Trigger an async deduplication run — identifies near-duplicate documents by measuring shared content across chunks and marks one per cluster as canonical
No parameter schema in public metadata yet.
dewey_get_duplicate_runGet the status and stats of the latest deduplication run (use to poll after `dewey_detect_duplicates`)
Get the status and stats of the latest deduplication run (use to poll after `dewey_detect_duplicates`)
No parameter schema in public metadata yet.
dewey_list_duplicate_groupsList near-duplicate groups with canonical + members and coverage percentages
List near-duplicate groups with canonical + members and coverage percentages
No parameter schema in public metadata yet.
dewey_promote_duplicate_canonicalPromote a different member to canonical; old canonical becomes near_duplicate
Promote a different member to canonical; old canonical becomes near_duplicate
No parameter schema in public metadata yet.
dewey_disband_duplicate_groupDisband a group; former members rejoin retrieval as distinct documents
Disband a group; former members rejoin retrieval as distinct documents
No parameter schema in public metadata yet.
dewey_get_collection_statsGet document count, storage, section/chunk/claim counts, and processing status breakdown
Get document count, storage, section/chunk/claim counts, and processing status breakdown
No parameter schema in public metadata yet.
dewey_update_collectionUpdate collection name, description, research instructions, visibility, and feature flags
Update collection name, description, research instructions, visibility, and feature flags
No parameter schema in public metadata yet.
dewey_recompute_summariesRe-run AI section summarization across all documents (e.g. after changing the LLM model)
Re-run AI section summarization across all documents (e.g. after changing the LLM model)
No parameter schema in public metadata yet.
dewey_recompute_captionsRe-run AI captioning for all images and tables across all documents
Re-run AI captioning for all images and tables across all documents
No parameter schema in public metadata yet.
dewey_delete_collectionPermanently delete a collection and all its data
Permanently delete a collection and all its data
No parameter schema in public metadata yet.
Sponsors
Configuration
DEWEY_API_KEY*secretYour Dewey project API key
DEWEY_COLLECTION_IDDefault collection ID. When set, tools that accept collection_id fall back to this value.
DEWEY_API_URLOverride the API base URL (default: https://api.meetdewey.com/v1)
Readme
@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.
Environment variables
Details
- Repository
- github.com/meetdewey/mcp
- Website
- meetdewey.com
- Categories
- AI & LLM Tools, Documents & Knowledge, Search & Web Crawling
- Package
@meetdewey/mcp- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active