Skip to main content
Glama
enesjakozh
Ritesh2351235

Omi Memories MCP Server

by Ritesh2351235
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Omi Memories MCP 服务器

这是一个模型上下文协议 (MCP) 服务器，通过工具界面为特定用户提供对 Omi 内存的访问。

特征

  • 用于从 OMI App 获取指定用户 ID 的所有记忆的工具

Related MCP server: MCP-Mem0

设置

  1. 安装依赖项：

npm install

  1. 配置您的用户 ID：

    • 打开src/server.ts

    • 使用 Omira 应用程序的“帐户”部分中的用户 ID 更新SPECIFIC_USER_ID常量

  2. 构建 TypeScript 代码：

npm run build

  1. 启动服务器：

npm start

可用工具

获取记忆

获取已配置用户 ID 的所有记忆。

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

const transport = new StdioClientTransport({
  command: "node",
  args: ["dist/server.js"]
});

const client = new Client(
  {
    name: "example-client",
    version: "1.0.0"
  },
  {
    capabilities: {
      tools: {}
    }
  }
);

await client.connect(transport);

// Fetch memories using the tool
const result = await client.callTool({
  name: "fetch-memories",
  arguments: {}
});
console.log(result.content[0].text);

配置

服务器期望：

  1. Express API 将在http://localhost:3000上运行

  2. 应配置用户 ID：将src/server.ts中的SPECIFIC_USER_ID常量更新为您可以从 Omira 应用程序的帐户部分获取的用户 ID。

Claude 桌面集成

要与 Claude Desktop 集成，请更新您的 Claude Desktop 配置（ claude_desktop_config.json ）以包含以下内容：

{
  "mcpServers": {
    "omi-mcp": {
      "command": "node",
      "args": [
        "/path/to/your/mcp-server/dist/server.js"
      ],
      "env": {
        "NODE_ENV": "development"
      }
    }
  }
}

Cursor IDE 集成

要与 Cursor IDE 集成：

  1. 打开 Cursor IDE 设置

  2. 导航至“AI 和 Copilot”设置

  3. 在“模型上下文协议”下，使用以下设置添加一个新的 MCP 服务器：

{
  "name": "Omi Memories",
  "command": "node",
  "args": [
    "/path/to/your/mcp-server/dist/server.js"
  ],
  "cwd": "/path/to/your/mcp-server",
  "env": {
    "NODE_ENV": "development"
  }
}

将/path/to/your/mcp-server替换为 MCP 服务器安装目录的实际路径。

Available Tools

1 tool
fetch-memoriesD
ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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 updatev1.0.0
    • Changedfetch-memories1 field changed
      • removedInput schema / additionalProperties
        Removed value: -false
  2. 1 tool update
    • First observedfetch-memories
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

D1.8/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'fetch-memories' stands alone with a distinct purpose, making disambiguation trivial.

Naming Consistency5/5

The single tool name 'fetch-memories' follows a clear verb_noun pattern. Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions to evaluate.

Tool Count2/5

A single tool is too few for a server named 'Omi Memories MCP Server', which suggests a domain involving memory storage or retrieval. This minimal set likely leaves significant functionality uncovered, making it inappropriate for the implied scope.

Completeness2/5

Inferred from the server name and tool name, the domain involves memories, but with only a fetch operation, there are obvious gaps such as creating, updating, deleting, or searching memories. This severely incomplete surface will cause agent failures in handling memory lifecycles.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches