Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "evalsmith-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "EVALSMITH_JUDGE_BASE_URL": "http://localhost:11434/v1",
        "EVALSMITH_JUDGE_MODEL": "llama3.1:8b",
        "EVALSMITH_JUDGE_API_KEY": "${EVALSMITH_JUDGE_API_KEY}",
        "LOG_LEVEL": "info"
      }
    }
  }
}

claude mcp add evalsmith-mcp -e "EVALSMITH_JUDGE_BASE_URL=http://localhost:11434/v1" -e "EVALSMITH_JUDGE_MODEL=llama3.1:8b" -e "EVALSMITH_JUDGE_API_KEY=${EVALSMITH_JUDGE_API_KEY}" -e "LOG_LEVEL=info" -- npx -y [email protected]

[mcp_servers.evalsmith-mcp]
command = "npx"
args = ["-y", "[email protected]"]
env = { "EVALSMITH_JUDGE_BASE_URL" = "http://localhost:11434/v1", "EVALSMITH_JUDGE_MODEL" = "llama3.1:8b", "EVALSMITH_JUDGE_API_KEY" = "${EVALSMITH_JUDGE_API_KEY}", "LOG_LEVEL" = "info" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "evalsmith-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "[email protected]"
      ],
      "enabled": true,
      "environment": {
        "EVALSMITH_JUDGE_BASE_URL": "http://localhost:11434/v1",
        "EVALSMITH_JUDGE_MODEL": "llama3.1:8b",
        "EVALSMITH_JUDGE_API_KEY": "{env:EVALSMITH_JUDGE_API_KEY}",
        "LOG_LEVEL": "info"
      }
    }
  }
}

{
  "mcpServers": {
    "evalsmith-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "EVALSMITH_JUDGE_BASE_URL": "http://localhost:11434/v1",
        "EVALSMITH_JUDGE_MODEL": "llama3.1:8b",
        "EVALSMITH_JUDGE_API_KEY": "${EVALSMITH_JUDGE_API_KEY}",
        "LOG_LEVEL": "info"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=evalsmith-mcp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImV2YWxzbWl0aC1tY3BAMC4xLjAiXSwiZW52Ijp7IkVWQUxTTUlUSF9KVURHRV9CQVNFX1VSTCI6Imh0dHA6Ly9sb2NhbGhvc3Q6MTE0MzQvdjEiLCJFVkFMU01JVEhfSlVER0VfTU9ERUwiOiJsbGFtYTMuMTo4YiIsIkVWQUxTTUlUSF9KVURHRV9BUElfS0VZIjoiJHtFVkFMU01JVEhfSlVER0VfQVBJX0tFWX0iLCJMT0dfTEVWRUwiOiJpbmZvIn19"
}

{
  "servers": {
    "evalsmith-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "EVALSMITH_JUDGE_BASE_URL": "http://localhost:11434/v1",
        "EVALSMITH_JUDGE_MODEL": "llama3.1:8b",
        "EVALSMITH_JUDGE_API_KEY": "${EVALSMITH_JUDGE_API_KEY}",
        "LOG_LEVEL": "info"
      }
    }
  }
}

{
  "mcpServers": {
    "evalsmith-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "EVALSMITH_JUDGE_BASE_URL": "http://localhost:11434/v1",
        "EVALSMITH_JUDGE_MODEL": "llama3.1:8b",
        "EVALSMITH_JUDGE_API_KEY": "${EVALSMITH_JUDGE_API_KEY}",
        "LOG_LEVEL": "info"
      }
    }
  }
}

extensions:
  "evalsmith-mcp":
    enabled: true
    name: "evalsmith-mcp"
    type: stdio
    cmd: "npx"
    args:
      - "-y"
      - "[email protected]"
    envs:
      "EVALSMITH_JUDGE_BASE_URL": "http://localhost:11434/v1"
      "EVALSMITH_JUDGE_MODEL": "llama3.1:8b"
      "EVALSMITH_JUDGE_API_KEY": "${EVALSMITH_JUDGE_API_KEY}"
      "LOG_LEVEL": "info"
    timeout: 300

Placeholders to fill from your own secret store: ${EVALSMITH_JUDGE_API_KEY}. The registry never accepts secret values.

This is a local package: the command runs on your machine.

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

protocoln/a · weight 25

n/a
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygienen/a · weight 30

n/a
tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dump, tools.hidden_texttool list unknown (behind auth, not probed, or empty)

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pull, stability.new_linkstool list unknown

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know [email protected]

Tool list unknown · checked 2026-11-14 07:36 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 91 / 100

provenance80

livenessn/a

freshness100

hygiene100

+repository +namespace-matches-repo ~liveness-unmeasured +updated-17d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

[email protected] npmthis version is not known to the dependency resolver

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

package	registry	version	runtime	secrets
`evalsmith-mcp`	npm	0.1.0	–	`EVALSMITH_JUDGE_API_KEY`

Tools (0)

No tools observed. Local packages are never executed by the registry.

Schemas: list_tools.

Similar MCP servers

More from io.github.diegoperezg7

Official server.json

{
  "name": "io.github.diegoperezg7/evalsmith-mcp",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "0.1.0",
  "packages": [
    {
      "version": "0.1.0",
      "transport": {
        "type": "stdio"
      },
      "identifier": "evalsmith-mcp",
      "registryType": "npm",
      "environmentVariables": [
        {
          "name": "EVALSMITH_JUDGE_BASE_URL",
          "format": "string",
          "default": "http://localhost:11434/v1",
          "description": "OpenAI-compatible endpoint for the optional LLM judge (default: Ollama on localhost)"
        },
        {
          "name": "EVALSMITH_JUDGE_MODEL",
          "format": "string",
          "default": "llama3.1:8b",
          "description": "Model used by the optional LLM judge"
        },
        {
          "name": "EVALSMITH_JUDGE_API_KEY",
          "format": "string",
          "isSecret": true,
          "description": "API key for the judge endpoint, if it needs one"
        },
        {
          "name": "LOG_LEVEL",
          "format": "string",
          "default": "info",
          "description": "pino log level; logs go to stderr"
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/diegoperezg7/evalsmith-mcp",
    "source": "github"
  },
  "description": "Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics."
}