Skip to main content
Glama
graph LR
    A["<b>.md files</b><br><i>Obsidian · Logseq · plain md</i>"] -- "watch + index" --> B["<b>mcp-recall-md</b><br><i>local vector store</i>"]
    C["<b>AI client</b><br><i>Claude · Cursor · Windsurf</i>"] -- "MCP search" --> B
    style A fill:#f9f4eb,stroke:#c9a96e,color:#333
    style B fill:#e8f0fe,stroke:#4a86c8,color:#333
    style C fill:#e8f5e9,stroke:#5b9a5b,color:#333

"Search my notes about Kubernetes networking"

→ finds kubernetes-networking.md (similarity: 0.53) — even though you phrased it differently than the note

  • Search by meaning, not keywords — finds notes even when your wording doesn't match

  • 100% offline — no API keys, no cloud, nothing leaves your machine

  • Zero config — point at your folders, restart your AI client, done

  • Real-time sync — file watcher picks up changes instantly, re-embeds only what changed


Quick start

Add to your MCP client config and restart:

{
  "mcpServers": {
    "mcp-recall-md": {
      "command": "uvx",
      "args": ["mcp-recall-md", "--vaults", "C:/Users/you/notes"]
    }
  }
}

Config file location: .mcp.json (Claude Code) · claude_desktop_config.json (Claude Desktop) · Cursor / Windsurf MCP settings

That's it. Your notes are searchable.


Related MCP server: Semantic Search MCP

Installation

The quick start above uses uvx (recommended). Other options:

pip install mcp-recall-md
{
  "mcpServers": {
    "mcp-recall-md": {
      "command": "mcp-recall-md",
      "args": ["--vaults", "C:/Users/you/notes"]
    }
  }
}
  1. Download mcp-recall-md.exe from the latest release

  2. Put it somewhere permanent (e.g. C:\Tools\mcp-recall-md\)

{
  "mcpServers": {
    "mcp-recall-md": {
      "command": "C:/Tools/mcp-recall-md/mcp-recall-md.exe",
      "args": ["--vaults", "C:/Users/you/notes"]
    }
  }
}

Configuration

Multiple vaults

List all folders — each is indexed independently:

"args": ["--vaults", "C:/notes/work", "C:/notes/personal", "C:/docs"]

.recallignore

Drop a .recallignore in any vault root to exclude files. Standard .gitignore syntax:

.obsidian/
_templates/
drafts/

CLI flags

Flag

Default

Description

--vaults

(none)

Folders to index and watch

--db-path

~/.mcp-recall-md/db

ChromaDB storage location

--verbose

off

Debug logging to stderr


Tools

Your AI assistant gets these tools automatically via MCP:

Tool

Description

search

Find notes by meaning — returns ranked results with similarity scores and file paths

status

Show indexed article count and watched vaults

index

Manually store an article (for use without --vaults)

remove

Delete an article from the index

Most users only interact with search — everything else is automatic.


Troubleshooting

Problem

Fix

Search returns nothing

Check that --vaults points to folders with .md files

First run is slow

Embedding model (~80 MB) downloads once on first use

Need to debug

Add --verbose, check ~/.mcp-recall-md/server.log

Force re-index

Delete ~/.mcp-recall-md/db and restart

Logs: ~/.mcp-recall-md/server.log (5 MB max, 3 rotated backups)


Limitations

  • Single-chunk embedding — large files (10k+ words) may search less precisely than shorter notes

  • English-optimized — other languages work but with lower accuracy


License

MIT

Available Tools

4 tools
indexB

Index a knowledge base article. Replaces any existing article with the same key.

Inputs: key (required), content (required). Returns: result

removeC

Remove an article from the knowledge base by key.

Inputs: key (required). Returns: result

statusA

Show the current state of the knowledge base: number of indexed articles and watched vaults.

Inputs: no named parameters. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clear and distinct purpose: index adds/replaces articles, remove deletes, search queries semantically, and status shows state. No ambiguity.

    Naming Consistency5/5

    All tool names are single lowercase verbs (index, remove, search, status), following a consistent and predictable pattern.

    Tool Count5/5

    4 tools is well-scoped for a knowledge base server, covering essential operations without being too few or too many.

    Completeness3/5

    The set covers add (index), delete (remove), and search, but lacks direct retrieval by key and a list-all-articles capability, which are notable gaps.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables semantic search over local Markdown documentation using hybrid retrieval combining embeddings, keyword search, and graph traversal with automatic file watching and zero-configuration setup.
      2
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables semantic search over markdown files to find related notes by meaning rather than keywords, and automatically detect duplicate content before creating new notes.
      3
      2
      BSD 2-Clause "Simplified"
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables semantic search over local notes and documents using natural language queries. Supports multiple file types (Markdown, Python, HTML, JSON, CSV, text) with fast local embeddings and persistent ChromaDB vector storage.
      1
      -
    • A
      license
      A
      quality
      D
      maintenance
      Provides semantic search and a tag-based knowledge graph for any project, auto-discovering local markdown knowledge bases with YAML frontmatter.
      10
      18 npm
      MIT