LocalFree

Evalsmith MCP server

diegoperezg7/evalsmith-mcp

Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.

1 GitHub stars379 npm downloads / month
Source code

Install Evalsmith in Claude Code

Claude Code
claude mcp add evalsmith -- npx -y evalsmith-mcp
mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)
{
  "mcpServers": {
    "evalsmith": {
      "command": "npx",
      "args": [
        "-y",
        "evalsmith-mcp"
      ]
    }
  }
}

Frequently asked questions

What does the Evalsmith MCP server do?

Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.

Is the Evalsmith MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does Evalsmith run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Evalsmith to Claude Code?

Run: claude mcp add evalsmith -- npx -y evalsmith-mcp

More knowledge, memory & rag MCP servers

View all

Global Agent Memory

14

ozankasikci/global-agent-memory

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

LocalFree

Brainbox

14471

thebasedcapital/brainbox

Hebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens.

LocalFree

Hushdrop

8170

maxtechera/hushdrop

Open-source artifact sharing for AI agents: private, branded, zero-knowledge links.

LocalFree

Attestor

14

bolnet/attestor

Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.

LocalFree

Obsidian CLI

2372

stonematt/mcp-obsidian-cli

Save chat notes from Claude Desktop to your vault — MCP on Obsidian CLI. Keep what matters.

LocalFree

Midas

14

vornicx/Midas

Local-first long-horizon agent memory: source-traceable recall, belief revision, selective forgetting and a guard against memory-driven destructive actions.

LocalFreePython