document-manager-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@document-manager-mcp list all feature specs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Document Manager MCP
An MCP (Model Context Protocol) server for managing product documentation as markdown files. Use it from Cursor, Claude Desktop, or any MCP client to create, read, update, delete, and search documentation.
Document types
All files are stored as markdown under a configurable project root, in these categories:
Type | Folder | Use for |
|
| Feature specifications |
|
| Jobs to be done |
|
| User stories |
|
| API documentation |
A special file docs/product-vision-and-strategy.md holds the product vision and strategy. Use the product_vision_and_strategy tool to view it and create it (with a default template) if it doesn’t exist.
Related MCP server: Markdown RAG MCP
Project identity (multiple MCPs)
When you run several Document Manager MCPs (e.g. one per project), set a project name so you can tell them apart in Cursor:
Environment variable:
DOCS_PROJECT_NAME— short label for this project (e.g.my-app,backend-api).The server then appears in Cursor as "document-manager (my-app)" instead of just "document-manager".
Example with two projects:
{
"mcpServers": {
"document-manager-my-app": {
"command": "npx",
"args": ["document-manager-mcp"],
"env": {
"DOCS_PROJECT_ROOT": "/path/to/my-app",
"DOCS_PROJECT_NAME": "my-app"
}
},
"document-manager-backend": {
"command": "npx",
"args": ["document-manager-mcp"],
"env": {
"DOCS_PROJECT_ROOT": "/path/to/backend",
"DOCS_PROJECT_NAME": "backend-api"
}
}
}
}You’ll see two MCPs: document-manager (my-app) and document-manager (backend-api).
Project root
Set the project root so the MCP knows where to read/write files:
Environment variable:
DOCS_PROJECT_ROOT(absolute or relative path).If unset, the server uses the current working directory when the server starts.
Example: if DOCS_PROJECT_ROOT=/Users/you/my-product, then:
Feature specs go in
/Users/you/my-product/docs/feature-specs/API docs go in
/Users/you/my-product/docs/api/, etc.
MCP tools
Tool | Description |
| List all docs, optionally filtered by type. |
| Read a doc by |
| Create or overwrite a doc (markdown content). |
| Create a new doc; fails if it already exists. |
| Delete a doc by type and slug. |
| Search by text. With |
| View the product vision and strategy doc; creates |
MCP resources
Docs are exposed as resources with URIs:
Pattern:
doc://{docType}/{slug}Examples:
doc://feature-specs/auth-spec.md,doc://api/users-endpoint.mdProduct vision and strategy:
doc://product-vision-and-strategy(single resource; create the file with theproduct_vision_and_strategytool if needed).
Clients can list and read these resources like files (e.g. in Cursor’s MCP resource UI).
Run with npx (recommended)
No install needed. Use npx so the package is run on demand:
npx document-manager-mcpWith environment variables:
DOCS_PROJECT_ROOT=/path/to/your/project DOCS_PROJECT_NAME=my-project npx document-manager-mcpIn Cursor (or another MCP client), configure the server to run via npx:
{
"mcpServers": {
"document-manager": {
"command": "npx",
"args": ["document-manager-mcp"],
"env": {
"DOCS_PROJECT_ROOT": "/ABSOLUTE/PATH/TO/YOUR/PROJECT",
"DOCS_PROJECT_NAME": "your-project"
}
}
}
}Replace /ABSOLUTE/PATH/TO/YOUR/PROJECT with the folder that should contain the docs/ tree. DOCS_PROJECT_NAME is optional; use it when you run multiple Document Manager MCPs so you can tell them apart.
Semantic search (local embeddings)
To search by meaning (e.g. “login” matching “authentication”, “sign-in”) instead of exact text only, use a local embedding model. No API key required.
Set in your MCP server env:
DOCS_EMBEDDING_PROVIDER=local— enables semantic search using Transformers.js and the default modelXenova/all-MiniLM-L6-v2(downloaded on first use, then cached).DOCS_EMBEDDING_MODEL(optional) — another Hugging Face model ID for feature extraction (e.g.Xenova/all-mpnet-base-v2for higher quality, larger download).
Example:
{
"mcpServers": {
"document-manager": {
"command": "npx",
"args": ["document-manager-mcp"],
"env": {
"DOCS_PROJECT_ROOT": "/path/to/your/project",
"DOCS_PROJECT_NAME": "my-project",
"DOCS_EMBEDDING_PROVIDER": "local"
}
}
}
}The first semantic search will build an index under .document-manager/embedding-index.json; later searches reuse it until docs change. You can pass mode: "keyword" to search_docs to force exact-text search, or mode: "semantic" when local embeddings are enabled.
Cursor setup
Configure Cursor
In Cursor: Settings → MCP (or edit your MCP config file). Add a server entry using npx and set the project root viaenv:{ "mcpServers": { "document-manager": { "command": "npx", "args": ["document-manager-mcp"], "env": { "DOCS_PROJECT_ROOT": "/ABSOLUTE/PATH/TO/YOUR/PROJECT", "DOCS_PROJECT_NAME": "your-project" } } } }Replace
/ABSOLUTE/PATH/TO/YOUR/PROJECTwith the folder that should contain thedocs/tree (feature-specs, jtbd, user-stories, api). UseDOCS_PROJECT_NAMEas a short label when you have multiple Document Manager MCPs (optional).Restart Cursor (or reload MCP) so it picks up the server.
Running from source
If you develop or fork this repo and want to run the built server without npx:
git clone https://github.com/rfbatista/document-manager-mcp.git
cd document-manager-mcp
npm install
npm run buildThen in your MCP config use "command": "node" and "args": ["/ABSOLUTE/PATH/TO/document-manager-mcp/build/index.js"].
Claude Desktop setup
Add the server to claude_desktop_config.json and run it with npx:
{
"mcpServers": {
"document-manager": {
"command": "npx",
"args": ["document-manager-mcp"],
"env": {
"DOCS_PROJECT_ROOT": "/ABSOLUTE/PATH/TO/YOUR/PROJECT",
"DOCS_PROJECT_NAME": "your-project"
}
}
}
}Development
npm install
npm run build # build once
npm run start # run built server (stdio)Use stderr for logs; stdout is used for MCP JSON-RPC.
License
MIT
document-manager-mcp
Available Tools
7 toolscreate_docB
Create a new documentation file with optional initial content. Use docType to choose category.
Inputs: slug (required), docType (required), content.
delete_docA
Delete a documentation file by type and slug.
Inputs: slug (required), docType (required).
list_docsA
List documentation files. Optionally filter by doc type (feature-specs, jtbd, user-stories, api).
Inputs: docType.
product_vision_and_strategyA
View the product vision and strategy document. Creates the file with a default template (docs/product-vision-and-strategy.md) if it does not exist.
Inputs: no named parameters.
read_docA
Read the content of a documentation file by type and slug (filename without path).
Inputs: slug (required), docType (required).
search_docsA
Search documentation by text. Use semantic search (by meaning) when local embeddings are enabled (DOCS_EMBEDDING_PROVIDER=local), otherwise keyword (case-insensitive) search.
Inputs: query (required), mode, limit, docType.
write_docA
Write or overwrite a documentation file. Content must be markdown. Creates parent folder if needed.
Inputs: slug (required), content (required), docType (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Most tools are distinct (list, read, delete, search), but write_doc and create_doc both can create files, and product_vision_and_strategy overlaps with read/create for a specific doc. The descriptions help differentiate, but an agent might misselect for creation tasks.
The verb_noun pattern (list_docs, read_doc, write_doc, create_doc, delete_doc, search_docs) is consistent, though singular/plural varies. product_vision_and_strategy breaks the pattern as a noun phrase.
Seven tools is appropriate for a document manager, covering core operations without bloat.
The set provides full CRUD (create via create_doc/write_doc, read, update via write_doc, delete), plus list and search. No obvious gaps for the domain.
Related MCP Connectors
Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.
MCP server for querying Forkast documentation
MCP server for Product Management
MCP server for innovationlab documentation, generated by doc2mcp.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceGeneric MCP server that exposes Markdown documentation to LLMs, enabling them to search and answer questions about any software documentation.MIT
- AlicenseNot gradedqualityDmaintenanceProvides semantic search over markdown documentation using RAG, allowing natural language queries and integration with MCP clients.1MIT
- AlicenseNot gradedqualityBmaintenanceMCP server for structured document management of markdown and YAML files, with RBAC, git-based approval workflows, and semantic search, enabling agents to read, edit, and maintain documents under governance.MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for documentation search that automatically indexes web documentation sites and provides semantic, full-text, or hybrid search capabilities.10 npmMIT