Koskamo

EvalView MCP

EvalView provides regression testing for AI agents by snapshotting behavior, diffing tool calls, and catching regressions in CI. It works with LangGraph, CrewAI, OpenAI, and Anthropic, allowing users to record agent baselines and detect changes in tool usage or output quality.

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

EvalView MCP logo, by hidai25Community listingLocal stdioSource reviewed; not executedPublished by hidai25
Vendor documentation

What you can do with it

  • Snapshot agent behavior as a baseline
  • Diff tool calls and parameters against baseline
  • Catch regressions in CI/CD pipelines
  • Verify agent output quality with LLM judge

Source and maintenance

Community listingRegistry 0.6.0
mcp-registry: io.github.hidai25/evalview-mcp@0.6.0Source repository
Maintenance checked

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

evalview 0.6.0

pypi
evalview package definition
{
  "version": "0.6.0",
  "transport": "stdio",
  "identifier": "evalview",
  "registryType": "pypi",
  "environmentVariables": [
    {
      "name": "OPENAI_API_KEY",
      "format": "string",
      "description": "OpenAI API key for LLM-as-judge output quality scoring. Optional — deterministic tool/sequence evaluation works without it."
    }
  ]
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.
Cursor configuration
{
  "mcpServers": {
    "evalview-mcp": {
      "command": "uvx",
      "args": [
        "evalview==0.6.0"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.
Cline configuration
{
  "mcpServers": {
    "evalview-mcp": {
      "command": "uvx",
      "args": [
        "evalview==0.6.0"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.
VS Code configuration
{
  "servers": {
    "evalview-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "evalview==0.6.0"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.
Claude Desktop configuration
{
  "mcpServers": {
    "evalview-mcp": {
      "command": "uvx",
      "args": [
        "evalview==0.6.0"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Let your agent find its tools

Find servers like EvalView MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 7,465