PluginBench
MCP Server
Active
MIT

OMEM MCP Server

io.github.troybrandonc-bit/omem

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the OMEM MCP server?

Memory for AI agents that tracks beliefs over time and surfaces contradictions

How to install OMEM

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • OMEM_API_KEY
    required
    secret

    API key from the OMEM server. It is printed on first run of `omem-server`.

  • OMEM_PROJECT
    required

    Project id to read and write memory in, also printed on first run.

  • OMEM_BASE_URL

    URL of the OMEM server.

  • OMEM_AGENT

    The agent whose memory this process reads and writes. Fixed here rather than passed as a tool argument, so the model cannot act as a different agent.

  • OMEM_USER

    The end user this process is acting for. Also fixed here, not a tool argument. Leave unset and no user-scoped memory is visible.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "omem": {
      "command": "uvx",
      "args": [
        "omem-infrastructure"
      ],
      "env": {
        "OMEM_API_KEY": "<YOUR_OMEM_API_KEY>",
        "OMEM_PROJECT": "<YOUR_OMEM_PROJECT>",
        "OMEM_BASE_URL": "<YOUR_OMEM_BASE_URL>",
        "OMEM_AGENT": "<YOUR_OMEM_AGENT>",
        "OMEM_USER": "<YOUR_OMEM_USER>"
      }
    }
  }
}

Related MCP servers

Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API.

0
TypeScript
Apache-2.0
View repository →

Risk guardrails for AI trading agents. Your agent proposes; your policy decides.

2
Python
MIT
View repository →
OPOpenRouter logo

MCP server providing access to 300+ AI models via OpenRouter

1
Python
MIT
View repository →

Intelligent memory layer for AI agents with semantic search, knowledge graphs, and automatic consolidation.

46
TypeScript
MIT
View repository →

Breach intelligence API: email search, domain monitoring, passwords and stealer logs.

XAXamlMcp logo

XamlMcp

Active

Inspect and drive Avalonia, WPF, WinUI, and .NET MAUI apps through AI with XAML tree inspection and automation.

24
C#
Apache-2.0
View repository →