memory-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_notesA | Read personal notes from the local filesystem. If no filename is provided, lists all available notes with metadata. If a filename is provided, returns the full content of that note. Args: filename: Optional. Name of the note file to read (e.g. "ideas.md"). If omitted, returns a list of all available notes. Returns: JSON string with note content or list of available notes. |
| semantic_searchA | Search personal notes and files by semantic meaning. Uses vector embeddings to find content related to your query, even if the exact words don't match. For example, searching "project deadlines" will find notes about "due dates" or "milestones". Args: query: Natural language description of what you're looking for. top_k: Number of results to return (1-20, default 5). Returns: JSON string with ranked search results and relevance scores. |
| get_recent_activityA | Get recent file system activity from watched directories. Shows the latest file changes (created, modified, deleted, moved) in your notes and files directories. Useful for understanding what you've been working on recently. Args: limit: Number of recent events to return (default 20, max 100). Returns: JSON string with recent file events and timestamps. |
| index_statsA | Get statistics about the vector search index. Shows how many documents/chunks are indexed, which embedding model is being used, and where the data is stored. Returns: JSON string with index statistics. |
| save_noteA | Save a new note or overwrite an existing one. Use this to write memories, meeting summaries, conversation notes, or any context back into the personal knowledge base. Args: filename: Name for the note file (e.g., "meeting-summary.md"). content: Full content to write. Returns: JSON string with saved file metadata. |
| append_noteA | Append content to an existing note. Use this to add follow-up context, action items, or updates to an existing note without overwriting it. Args: filename: Name of the existing note file. content: Content to append. Returns: JSON string with updated file metadata. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Shaktisinhchavda/memory-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server