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.
OPENROUTER_API_KEYrequiredsecretOpenRouter API key — required for the default chat LLM (PINRAG_LLM_PROVIDER defaults to openrouter). Get a key at openrouter.ai.
PINRAG_PERSIST_DIRAbsolute path to the Chroma vector store directory (recommended so indexes are not tied to the server process cwd).
{
"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).

io.github.negm17111995/circlfi-mcp
13-model stock valuation engine for AI agents - fair values for 5,900+ US stocks, updated daily.
Ranked economic opportunities, market evidence, experiments, and margin intelligence for AI agents.

Query multiple LLMs simultaneously—OpenAI-compatible APIs and CLI agents—for diverse perspectives, voting, debates, and consensus.
Refund eligibility notary for US subscriptions. Returns ALLOWED/DENIED/UNKNOWN.
Agentic identity trust: precision decisioning, cryptographic release tokens, hash-chained proof
View repository →


