Click on "Install 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., "@Memos MCP Server search for memos tagged 'meeting' from last week"
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.
An MCP (Model Context Protocol) server that provides tools for interacting with a Memos instance. This server allows AI assistants to search, create, and update memos through the Memos API.
Search Memos: Search for memos with filters like creator, tags, visibility, and content
Create Memos: Create new memos with markdown support
Update Memos: Update existing memos (content, visibility, pinned status)
Get Memo: Retrieve a specific memo by UID
Related MCP server: MCP Server for Mem.ai
Clone this repository:
git clone <repository-url>
cd memos_mcpInstall dependencies:
uv syncpip install -r requirements.txtSet the following environment variables:
MEMOS_BASE_URL: The base URL of your Memos instance (default: http://localhost:5230)
MEMOS_API_TOKEN: Your Memos API authentication token (optional for public instances)
Log into your Memos instance
Go to Settings → Access Tokens
Create a new access token
Copy the token and set it as the MEMOS_API_TOKEN environment variable
Example:
export MEMOS_BASE_URL="https://memos.example.com"
export MEMOS_API_TOKEN="your-token-here"# Run directly with uvx
uvx --from . memos-mcp# After running 'uv sync'
uv run memos-mcpfastmcp run server.pyfrom server import mcp
# The server is ready to useSearch for memos with optional filters.
Parameters:
query (optional): Text to search for in memo content
creator_id (optional): Filter by creator user ID
tag (optional): Filter by tag name
visibility (optional): Filter by visibility (PUBLIC, PROTECTED, PRIVATE)
limit (default: 10): Maximum number of results
offset (default: 0): Number of results to skip
Example:
result = await search_memos(query="meeting notes", limit=5)Create a new memo.
Parameters:
content: The content of the memo (supports Markdown)
visibility (default: PRIVATE): Visibility level (PUBLIC, PROTECTED, PRIVATE)
Example:
result = await create_memo(
content="# Meeting Notes\n\n- Discuss project timeline\n- Review budget",
visibility="PRIVATE"
)Update an existing memo.
Parameters:
memo_uid: The UID of the memo to update
content (optional): New content for the memo
visibility (optional): New visibility level
pinned (optional): Whether to pin the memo
Example:
result = await update_memo(
memo_uid="abc123",
content="Updated content",
pinned=True
)Get a specific memo by its UID.
Parameters:
memo_uid: The UID of the memo to retrieve
Example:
result = await get_memo(memo_uid="abc123")Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"memos": {
"command": "uvx",
"args": ["--from", "/path/to/memos_mcp", "memos-mcp"],
"env": {
"MEMOS_BASE_URL": "http://localhost:5230",
"MEMOS_API_TOKEN": "your-token-here"
}
}
}
}{
"mcpServers": {
"memos": {
"command": "uv",
"args": ["run", "--directory", "/path/to/memos_mcp", "memos-mcp"],
"env": {
"MEMOS_BASE_URL": "http://localhost:5230",
"MEMOS_API_TOKEN": "your-token-here"
}
}
}
}{
"mcpServers": {
"memos": {
"command": "python",
"args": ["-m", "fastmcp", "run", "/path/to/memos_mcp/server.py"],
"env": {
"MEMOS_BASE_URL": "http://localhost:5230",
"MEMOS_API_TOKEN": "your-token-here"
}
}
}
}This server is built on the Memos API v1. The API follows Google's API Improvement Proposals (AIPs) design guidelines.
GET /api/v1/memos - List/search memos
POST /api/v1/memos - Create a memo
GET /api/v1/memos/{uid} - Get a specific memo
PATCH /api/v1/memos/{uid} - Update a memo
The server supports Bearer token authentication. Include your access token in the Authorization header:
Authorization: Bearer your-token-herepytestserver.py: Main MCP server implementation with all tools
requirements.txt: Python dependencies
Memos is a lightweight, self-hosted memo hub with knowledge management and social networking features. Learn more at:
Website: https://www.usememos.com/
MIT License - see LICENSE file for details
Contributions are welcome! Please feel free to submit a Pull Request.
Create a new memo.
Args: content: The content of the memo (supports Markdown) visibility: Visibility level - PUBLIC, PROTECTED, or PRIVATE (default: PRIVATE)
Returns: JSON string containing the created memo details
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| visibility | No | PRIVATE |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. While it mentions the tool creates a memo and returns JSON, it doesn't address important behavioral aspects like authentication requirements, error conditions, rate limits, or whether the operation is idempotent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and well-structured with clear sections for Args and Returns. Each sentence adds value, though the 'Create a new memo' statement is somewhat redundant with the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there's an output schema (which handles return value documentation) and the description compensates well for the 0% schema description coverage, this is adequate. However, for a creation tool with no annotations, more behavioral context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds significant value beyond the input schema, which has 0% description coverage. It explains that 'content' supports Markdown and defines the three possible values for 'visibility' (PUBLIC, PROTECTED, PRIVATE) along with the default. This compensates well for the schema's lack of descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool creates a new memo, which is a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'update_memo' or explain when to use this versus 'search_memos' for finding existing memos.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives. The description doesn't mention prerequisites, when not to use it, or how it relates to sibling tools like 'get_memo', 'search_memos', or 'update_memo'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a specific memo by its UID.
Args: memo_uid: The UID of the memo to retrieve (e.g., "abc123")
Returns: JSON string containing the memo details
| Name | Required | Description | Default |
|---|---|---|---|
| memo_uid | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool retrieves memo details but lacks information on permissions needed, error handling (e.g., what happens if the UID is invalid), rate limits, or whether it's a read-only operation. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, starting with the core purpose followed by structured sections for Args and Returns. Every sentence adds value without redundancy, making it efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 parameter) and the presence of an output schema, the description is largely complete. It covers the purpose, parameter semantics, and return format. However, it could benefit from more behavioral details like error handling or permissions, which are not addressed in annotations or output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaningful context beyond the input schema by explaining that memo_uid is 'The UID of the memo to retrieve' and provides an example ('e.g., "abc123"'). Since schema description coverage is 0%, this compensates well, though it could detail format constraints or validation rules more explicitly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Get') and resource ('a specific memo by its UID'), distinguishing it from sibling tools like create_memo, search_memos, and update_memo. It precisely defines what the tool does without being vague or tautological.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by specifying retrieval by UID, suggesting it's for when you know the exact memo identifier. However, it does not explicitly state when to use this tool versus alternatives like search_memos, which might be for broader queries, leaving some guidance implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for memos with optional filters.
Args: query: Text to search for in memo content creator_id: Filter by creator user ID tag: Filter by tag name visibility: Filter by visibility (PUBLIC, PROTECTED, PRIVATE) limit: Maximum number of results to return (default: 10) offset: Number of results to skip (default: 0)
Returns: JSON string containing the list of matching memos
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| creator_id | No | ||
| tag | No | ||
| visibility | No | ||
| limit | No | ||
| offset | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool 'Returns: JSON string containing the list of matching memos,' which adds some context about the output format. However, it doesn't describe critical behaviors like whether this is a read-only operation (implied but not stated), pagination details beyond limit/offset, error handling, or any rate limits. For a search tool with zero annotation coverage, this leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and well-structured. It starts with a clear purpose statement, followed by a bulleted 'Args' section that efficiently documents each parameter, and ends with a 'Returns' statement. Every sentence earns its place by providing essential information without redundancy or fluff, making it easy to scan and understand.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (a search tool with 6 parameters), no annotations, and an output schema (implied by 'Has output schema: true'), the description is mostly complete. It thoroughly documents parameters and mentions the return format. However, it lacks behavioral details like read-only confirmation, error cases, or pagination context, which would be helpful despite the output schema. For a tool with no annotations, it does well but has minor gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must fully compensate. It provides detailed semantics for all 6 parameters in the 'Args' section, explaining what each filter does (e.g., 'query: Text to search for in memo content,' 'visibility: Filter by visibility (PUBLIC, PROTECTED, PRIVATE)'), including default values. This adds substantial meaning beyond the bare schema, fully documenting parameter purposes and usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as 'Search for memos with optional filters,' which is a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'get_memo' (which likely retrieves a single memo by ID) or 'create_memo'/'update_memo' (which are write operations). The purpose is clear but lacks sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to prefer 'search_memos' over 'get_memo' (e.g., for filtering vs. direct ID lookup) or any prerequisites like authentication needs. There's only implied usage based on the tool name and parameters, with no explicit context or exclusions provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update an existing memo.
Args: memo_uid: The UID of the memo to update (e.g., "abc123") content: New content for the memo (optional) visibility: New visibility level - PUBLIC, PROTECTED, or PRIVATE (optional) pinned: Whether to pin the memo (optional)
Returns: JSON string containing the updated memo details
| Name | Required | Description | Default |
|---|---|---|---|
| memo_uid | Yes | ||
| content | No | ||
| visibility | No | ||
| pinned | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only states it 'updates an existing memo' without disclosing behavioral traits like permission requirements, whether partial updates are allowed, error conditions, or rate limits. The return format is mentioned but lacks detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized with clear sections for Args and Returns. The opening sentence is front-loaded with the core purpose. Some minor verbosity exists in listing all parameter details that could be inferred from schema, but overall structure is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 parameters with 0% schema coverage and no annotations, the description does well on parameter semantics but lacks behavioral context for a mutation tool. The presence of an output schema reduces need to explain return values, but more guidance on usage and transparency would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It provides clear semantic explanations for all 4 parameters: memo_uid identifies the target, content is new text, visibility has enumerated values, and pinned controls pinning status. This adds significant value beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'update' and resource 'memo', making the purpose immediately understandable. However, it doesn't differentiate this tool from its sibling 'create_memo' beyond the obvious difference in operation type, missing explicit comparison.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives like 'create_memo' or 'get_memo'. The description simply states what the tool does without context about appropriate use cases or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose with no overlap: create_memo for creation, get_memo for retrieval by UID, search_memos for filtered searching, and update_memo for modifications. The actions (create, get, search, update) target the same resource (memos) but operate in non-overlapping ways, making misselection unlikely.
All tool names follow a consistent verb_noun pattern with 'memo' as the noun: create_memo, get_memo, search_memos, update_memo. The pattern is uniform throughout, using snake_case and clear action verbs, making the set predictable and easy to understand.
With 4 tools, this server is well-scoped for a memos management system. Each tool earns its place by covering essential CRUD operations (create, get, update) plus search functionality, which is appropriate for the domain without being overly sparse or bloated.
The tool set covers core CRUD operations (create, get, update) and search, but lacks a delete_memo tool for full lifecycle coverage. This minor gap might require workarounds for deletion tasks, though the existing tools support most common workflows effectively.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Securely search, create, and organize your Mem notes and collections from AI assistants.
Connect AI to your flomo notes. Search, create, edit notes and manage tags via MCP.
Search, read, create and edit your Memol notes from Claude. Team note-taking with AI search.
Persistent cloud memory for AI agents. Store and search key-value memories across sessions.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Red5d/memos_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
