MCP server
Evalgate
io.github.ipezygj/evalgate
Checked 25 Oct 2026, 21:11 UTC · Removed from its registry; checked against OSV.dev; never run by us
Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).
Runs on your computerRemoved from its registry: not on PyPI (version 0.4.1)
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Runs on your computer
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code
- Last checked
- 25 Oct 2026, 21:11 UTC
Connect it to your agent
Claude Code
claude mcp add evalgate -- uvx eval-integrity@0.4.1
Claude Desktop
{"mcpServers":{"evalgate":{"command":"uvx","args":["eval-integrity@0.4.1"]}}}
Codex (config.toml)
[mcp_servers.evalgate] command = "uvx" args = ["eval-integrity@0.4.1"]
Gemini CLI
{"mcpServers":{"evalgate":{"command":"uvx","args":["eval-integrity@0.4.1"]}}}
Cursor
{"mcpServers":{"evalgate":{"command":"uvx","args":["eval-integrity@0.4.1"]}}}
VS Code
{"servers":{"evalgate":{"type":"stdio","command":"uvx","args":["eval-integrity@0.4.1"]}}}
Runs on your computer with your permissions: check the package and its source before installing.
Browse
Related MCP servers
- Money Mind — the judge
Statistical adjudication for agents: backtest judges, fact-checks. Pay per call in USDC via x402. - Rubrkit
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output. - Babyblueviper Invinoveritas
Second opinion before an irreversible agent action; signed proofs, free verify, public ledger. - Sparkling Tracks Tours
Read-only MCP for Sparkling Tracks European tours: packages, itineraries, pricing, contacts. - SCRIPTMASTERLABS — Provider Trust + CANON
Provider Trust MCP: verify providers before agents trust them + CANON bulk registry lookup (x402). - Aval
Payment-backed trust scores for AI agents on Base (ERC-8004). $0.01 per check via x402. - ZeroWidth Caliper
Build datasets and rubrics, then run evals that score your AI in Caliper. - Nordax AI Entity Network
Search and verify 360K+ business entities with trust scores and W3C credentials.
Badge for your README
[](https://aptlynx.net/servers/io.github.ipezygj/evalgate)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents