retriEVAL MCP Server
io.github.hcarrillo001/retrieval-mcp
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 retriEVAL MCP server?
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
How to install retriEVAL
Copy-paste configuration for popular MCP clients.
ANTHROPIC_API_KEYsecretJudge model API key. Not needed if you set RETRIEVAL_JUDGE_BACKEND=ollama to run the judge locally.
RETRIEVAL_JUDGE_BACKENDWhich judge to score with: anthropic (default), openai, or ollama for a fully local judge.
RETRIEVAL_JUDGE_MODELJudge model id, e.g. claude-sonnet-4-6 or qwen2.5:14b for Ollama.
RETRIEVAL_BUDGET_USDSpend cap for judge calls. Unset means no cap.
{
"mcpServers": {
"retrieval-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/hcarrillo001/retrieval-mcp:1.0.0"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"RETRIEVAL_JUDGE_BACKEND": "<YOUR_RETRIEVAL_JUDGE_BACKEND>",
"RETRIEVAL_JUDGE_MODEL": "<YOUR_RETRIEVAL_JUDGE_MODEL>",
"RETRIEVAL_BUDGET_USD": "<YOUR_RETRIEVAL_BUDGET_USD>"
}
}
}
}Related MCP servers

Computer-Use Agents API
Run and manage H Company's Computer-Use Agents from any MCP client with browser automation and custom tools.

TokenLab MCP Server
TokenLab MCP server: 31 default and 80 full-profile tools for models, media, tasks, and files.

io.github.heidiEC/context-pod
Persistent context for AI agents built fromlearned vectors with certainty scores.
Behavioral memory layer that learns your preferences and context across Claude, Cursor, and Codex.
Independent MCP server for the Housecall Pro API: jobs, estimates, invoices, price book, schedule.
Local deterministic calc MCP: exact math, dates, unit conversion, stats, subnet math.


