PluginBench
MCP Server
Active
MIT

Gemdex MCP Server

io.github.nikships/gemdex

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 Gemdex MCP server?

Persistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB

How to install Gemdex

Copy-paste configuration for popular MCP clients.

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

    Google AI Studio key for local mode, or the exact value 'local' for on-device MLX text embeddings. Not needed in remote mode.

  • GEMDEX_MODE

    Memory backend: embedded local LanceDB or a self-hosted Gemdex Server

  • LANCEDB_PATH

    Directory for the embedded LanceDB store

  • EMBEDDING_MODEL

    Gemini text embedding model

  • GEMDEX_REMOTE_URL

    Gemdex Server root URL (required in remote mode)

  • GEMDEX_REMOTE_TOKEN
    secret

    Gemdex Server bearer token (required in remote mode)

  • GEMDEX_REMOTE_NAME

    Human-readable name for the remote server

  • GEMDEX_TRUST_RANKING

    Re-rank recall results by recorded worked/failed/stale outcomes

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "gemdex": {
      "command": "npx",
      "args": [
        "-y",
        "gemdex-mcp",
        "-y",
        "gemdex-mcp@1.0.47"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "GEMDEX_MODE": "<YOUR_GEMDEX_MODE>",
        "LANCEDB_PATH": "<YOUR_LANCEDB_PATH>",
        "EMBEDDING_MODEL": "<YOUR_EMBEDDING_MODEL>",
        "GEMDEX_REMOTE_URL": "<YOUR_GEMDEX_REMOTE_URL>",
        "GEMDEX_REMOTE_TOKEN": "<YOUR_GEMDEX_REMOTE_TOKEN>",
        "GEMDEX_REMOTE_NAME": "<YOUR_GEMDEX_REMOTE_NAME>",
        "GEMDEX_TRUST_RANKING": "<YOUR_GEMDEX_TRUST_RANKING>"
      }
    }
  }
}

Related MCP servers

Fast image generation with Google Gemini 3.1 Flash: 512px–4K, reference images, Google Search grounding, and transparent backgrounds.

14
Python
View repository →

Access Alibaba Cloud DashScope Qwen models for chat, embeddings, and model discovery via MCP.

218
JavaScript
Apache-2.0
View repository →

Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture for 3D agents.

218
JavaScript
Apache-2.0
View repository →

Set autopilot scopes and daily SOL spend caps, then propose, execute, and undo agent actions on-chain.

218
JavaScript
Apache-2.0
View repository →
PRPrismHR MCP logo

PrismHR MCP

Maintained

Open-source MCP server for PrismHR. PEO workflow tools + Microsoft 365 connectors.

3
Python
View repository →

Read and reply to your personal Telegram chats and all your Slack workspaces.

0
TypeScript
MIT
View repository →