Developer · Local MCP server
retriEVAL
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.hcarrillo001/retrieval-mcp- Version
- 1.0.0
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- OCI image (Docker)
- Published
- 2026-08-24
- Updated
- 2026-08-24
- Publisher
- hcarrillo001 (GitHub)
- Website
- retrieval-mcp.com
- Repository
- github.com/hcarrillo001/retrieval-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| OCI image (Docker) | ghcr.io/hcarrillo001/retrieval-mcp:1.0.0 | — | stdio |
How to connect retriEVAL
retriEVAL runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/hcarrillo001/retrieval-mcp:1.0.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm -e ANTHROPIC_API_KEY -e RETRIEVAL_JUDGE_BACKEND -e RETRIEVAL_JUDGE_MODEL -e RETRIEVAL_BUDGET_USD ghcr.io/hcarrillo001/retrieval-mcp:1.0.0. It reads these environment variables: ANTHROPIC_API_KEY (secret), RETRIEVAL_JUDGE_BACKEND, RETRIEVAL_JUDGE_MODEL and RETRIEVAL_BUDGET_USD; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"retrieval-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"ANTHROPIC_API_KEY",
"-e",
"RETRIEVAL_JUDGE_BACKEND",
"-e",
"RETRIEVAL_JUDGE_MODEL",
"-e",
"RETRIEVAL_BUDGET_USD",
"ghcr.io/hcarrillo001/retrieval-mcp:1.0.0"
],
"env": {
"ANTHROPIC_API_KEY": "<secret>",
"RETRIEVAL_JUDGE_BACKEND": "<value>",
"RETRIEVAL_JUDGE_MODEL": "<value>",
"RETRIEVAL_BUDGET_USD": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| retain-so MCP-SERVERModel Context Protocol server for Retain: let AI agents query churn risk and act on retention. | Local · stdio |
| RetascThe issue tracker AI coding agents pull work from: atomic claims, dependency-aware dispatch. | Remote · HTTP |
| Retell AIRetell AI MCP server: voice agent phone calls, agent management, LLMs, and voice discovery. | Local · stdio |
| RetentionCheckPull churn from Stripe, Postgres, MySQL, or pasted feedback. AI-ranked drivers + fixes. | Local · stdio |
| Retry TraceInspect external HTTPS 429/503 retries with server-recorded attempts, Retry-After and arrival times. | Remote · HTTP |
| Reuse Before GenerateChecks whether your idea already exists before your agent builds it. Searches GitHub, npm, Python. | Local · stdio |
| Reversecore MCPSecurity-first MCP server for reverse engineering, malware analysis, forensics, and SAST. | Local · stdio |
| Review Intelligence MCP ServerG2, Trustpilot, Yelp reviews with sentiment and theme extraction across sources. | Remote · HTTP |