retriEVAL
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
- Pricing
- Open source
- Runs
- Locally
- Version
- 1.0.0
- Listing updated
- 4 days ago
About retriEVAL
retriEVAL is an open-source MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.
Install
Run in a terminal
claude mcp add retrieval-mcp --env ANTHROPIC_API_KEY='<ANTHROPIC_API_KEY>' -- docker run -i --rm -e ANTHROPIC_API_KEY ghcr.io/hcarrillo001/retrieval-mcp:1.0.0Add to claude_desktop_config.json
{
"mcpServers": {
"retrieval-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANTHROPIC_API_KEY",
"ghcr.io/hcarrillo001/retrieval-mcp:1.0.0"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"retrieval-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANTHROPIC_API_KEY",
"ghcr.io/hcarrillo001/retrieval-mcp:1.0.0"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"retrieval-mcp": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANTHROPIC_API_KEY",
"ghcr.io/hcarrillo001/retrieval-mcp:1.0.0"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"retrieval-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANTHROPIC_API_KEY",
"ghcr.io/hcarrillo001/retrieval-mcp:1.0.0"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"retrieval-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANTHROPIC_API_KEY",
"ghcr.io/hcarrillo001/retrieval-mcp:1.0.0"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}Configuration
ANTHROPIC_API_KEYJudge 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.
Pricing
Open source
Prices change. Check retrieval-mcp.com before you buy.
retriEVAL FAQ
Is retriEVAL free?
Yes. retriEVAL is open source, so you can use and self-host it for free.
How do I add retriEVAL to Claude Code?
Run this command in your terminal: claude mcp add retrieval-mcp --env ANTHROPIC_API_KEY='<ANTHROPIC_API_KEY>' -- docker run -i --rm -e ANTHROPIC_API_KEY ghcr.io/hcarrillo001/retrieval-mcp:1.0.0
What are the best alternatives to retriEVAL?
The closest alternatives to retriEVAL are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.
Alternatives to retriEVAL

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

Nautilus Compass Memory
MCP serverLocal-first long-term memory layer for AI agents, served over MCP
Not checked yet- 5 tools
- Remote
- Open source
- 1.3K GitHub stars
- Knowledge and memory

note1
MCP serverMCP server giving AI assistants search and summaries across your note1 meetings
- 4 tools
- Remote
- Free trial
- 1 GitHub star
- Productivity
MedXpert 图书馆连接器(通用版)
MCP serverLocal MCP server that searches and answers questions over your own Markdown wiki
Runs locally- 4 tools
- Open source
- Knowledge and memory