Skip to main content
Glama
agcraft

memopaper-mcp

by agcraft
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

memopaper-mcp

MCP server for memopaper — gives AI agents direct access to your memo buffer.

Configuration

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "memopaper": {
      "command": "npx",
      "args": ["memopaper-mcp@latest"],
      "env": {
        "MEMOPAPER_API_KEY": "mp_..."
      }
    }
  }
}

Claude Code

Add .mcp.json to your project root:

{
  "mcpServers": {
    "memopaper": {
      "command": "npx",
      "args": ["memopaper-mcp@latest"],
      "env": {
        "MEMOPAPER_API_KEY": "mp_..."
      }
    }
  }
}

Get your API key at memopaper.dev under Dashboard → API Keys.

Note: Never commit .mcp.json containing your API key to version control. Add it to .gitignore.

Related MCP server: mem0_mcp_server

Tool

Exposes a single memo tool with the following actions:

Action

Description

Required params

add

Save a memo

text

list

List memos

—

get

Get a memo by UUID

uuid

get_nth

Get the Nth latest memo (1=newest)

index

latest

Get the latest memo

—

oldest

Get the oldest memo

—

pop

Get and delete the latest memo

—

delete

Delete a memo by UUID

uuid

edit

Edit a memo's text

uuid, text

stats

Show total count and per-group breakdown

—

Optional params on most actions: group, visibility, limit.

Environment Variables

Variable

Required

Description

MEMOPAPER_API_KEY

Yes

API key from the dashboard, starting with mp_

Claude Code Skills

For Claude Code users, optional slash commands are available in the skills/ directory:

Skill

Description

skills/watch.md

/memopaper:watch — watch a group and execute memos sequentially

skills/help.md

/memopaper:help — show usage help

Install:

mkdir -p ~/.claude/commands/memopaper
cp skills/watch.md ~/.claude/commands/memopaper/watch.md
cp skills/help.md  ~/.claude/commands/memopaper/help.md

Usage:

/memopaper:watch @tasks
/memopaper:watch @tasks 10
/memopaper:watch @tasks --shell

Warning: All memo execution — whether as AI instructions or shell commands — runs on your machine with your permissions. You are fully responsible for the content and consequences of every memo in the queue. Use only with memo groups you fully control and trust.

Shell execution is disabled by default. Pass --shell to enable it. Even then, destructive commands (rm, del, git reset --hard, dd, etc.) are automatically blocked and logged to @warning.

Related

Available Tools

1 tool
memoA

Save a memo or manage existing ones.

Actions and required parameters: add : text(req), group, visibility list : group, visibility, limit get : uuid(req) get_nth : index(req, 1=latest), group latest : group, visibility oldest : group, visibility pop : group — read + delete latest (destructive) delete : uuid(req) (destructive) edit : uuid(req), text(req) stats : (no params) — total and per-group count

ParametersJSON Schema
NameRequiredDescriptionDefault
textNoMemo content (max 2048 bytes). Required for: add, edit
uuidNoMemo UUID. Required for: get, delete, edit
groupNoGroup name filter/target (default: inbox)
indexNo1-based index (1=latest). Required for: get_nth
limitNoMax results (default: 20). Used in: list
actionYes
visibilityNoVisibility. Used in: add, list, latest, oldest

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description explicitly flags 'pop' as 'read + delete latest (destructive)' and marks 'delete' as destructive, which discloses important side effects. It also lists all actions, making the tool's behavior predictable. It does not mention errors, permissions, or idempotency, but the destructive labeling is a positive contribution given the absence of annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and information-dense, using a clear 'action: parameters' format. It front-loads the tool's purpose and provides a complete action list in just a few lines, without redundant prose. Every line serves to clarify an action, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's multi-action complexity and absence of output schema, the description covers all actions, required parameters, and destructive operations. It lacks return-type descriptions, but those are not explicitly required. The description is sufficient for an agent to select and invoke actions correctly, though a brief note on expected outputs would enhance completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already covers 86% of parameters with descriptions, including 'Required for' annotations for text, uuid, index, limit, and visibility. The description essentially restates this information in the action list, adding little new meaning beyond the schema. It does clarify that 'group' defaults to 'inbox', which is also present in the schema. Overall, the description does not significantly augment the schema's parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as managing memos, enumerating all 10 actions (add, list, get, get_nth, latest, oldest, pop, delete, edit, stats) with required parameters. While 'Save a memo or manage existing ones' is a bit generic, the action list clarifies the full scope and distinguishes the multiple operations available.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Each action's required and optional parameters are listed, which serves as operational guidance for how to use the tool. However, there is no explicit statement of when to use this tool versus alternatives, nor any context for typical use cases. Given there are no siblings, the lack of comparison is not a major flaw, but a sentence on recommended usage would have been helpful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 1 tool updatev1.0.3
    • First observedmemo
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no risk of confusing separate tools. The internal actions (add, list, get, delete, etc.) are distinct and well-named, making selection unambiguous.

Naming Consistency4/5

The tool is named 'memo' and uses simple verb-based actions. While the verb_noun pattern is not used at the tool level, the internal actions are consistently lowercase verbs, and the overall naming is predictable and readable.

Tool Count3/5

A single tool is quite thin for a tool surface, even though it packs many operations. The server would benefit from splitting actions into separate tools, but the current count is not a functional problem.

Completeness5/5

The tool provides full CRUD plus list, search-by-index, latest/oldest, pop (read+delete), and stats. This covers the memo domain thoroughly, leaving no obvious dead ends.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Memos MCP Server

    kinmeic
    A
    license
    A
    quality
    D
    maintenance
    MCP server for creating, listing, updating, deleting memos, and managing attachments via the Memos API.
    12
    10 npm
    MIT
  • @memofs/mcp-server by memo-fs

    @memofs/mcp-serverofficial

    memo-fs
    A
    license
    Not graded
    quality
    B
    maintenance
    @memofs/mcp-server lets AI coding agents (Claude Code, Claude Desktop, Codex, Cursor, opencode, Gemini CLI, GitHub Copilot, Zed, and any other MCP client) securely read and write MemoFS memory through standard Model Context Protocol tools.
    6
    MIT