PluginBench
MCP Server
Maintained
MIT

PinRAG MCP Server

io.github.ndjordjevic/pinrag

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 PinRAG MCP server?

MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.

How to install PinRAG

Copy-paste configuration for popular MCP clients.

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

    OpenRouter API key — required for the default chat LLM (PINRAG_LLM_PROVIDER defaults to openrouter). Get a key at openrouter.ai.

  • PINRAG_PERSIST_DIR

    Absolute path to the Chroma vector store directory (recommended so indexes are not tied to the server process cwd).

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "pinrag": {
      "command": "uvx",
      "args": [
        "pinrag",
        "--refresh",
        "pinrag"
      ],
      "env": {
        "OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
        "PINRAG_PERSIST_DIR": "<YOUR_PINRAG_PERSIST_DIR>"
      }
    }
  }
}

Related MCP servers

Verifiable entropy, provably-fair games, and receipt verification for AI agents (FairSeal API).

0
TypeScript
MIT
View repository →

13-model stock valuation engine for AI agents - fair values for 5,900+ US stocks, updated daily.

0
JavaScript
ISC
View repository →

Ranked economic opportunities, market evidence, experiments, and margin intelligence for AI agents.

0
JavaScript
View repository →

Query multiple LLMs simultaneously—OpenAI-compatible APIs and CLI agents—for diverse perspectives, voting, debates, and consensus.

175
TypeScript
MIT
View repository →

Refund eligibility notary for US subscriptions. Returns ALLOWED/DENIED/UNKNOWN.

1
JavaScript
View repository →

Agentic identity trust: precision decisioning, cryptographic release tokens, hash-chained proof

View repository →