How to choose
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.ipezygj/evalgate MCP server?
Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).
How to install io.github.ipezygj/evalgate
Copy-paste configuration for popular MCP clients.
transport: stdio
Config generated by PluginBench — verify against the source before use.~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
"mcpServers": {
"evalgate": {
"command": "uvx",
"args": [
"eval-integrity"
]
}
}
}Related MCP servers
IO

Verify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts.
0
View repository →Python
MIT
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
View repository →IR

Iris
Active
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
7
View repository →TypeScript
MIT
IP

IPinfo
Active
Official IPinfo MCP Server - IP intelligence tools for AI assistants
1
View repository →Python
Apache-2.0
AG

Agent Memory MCP
Active
Memory, docs, and repo context layer for engineering agents with typed storage, RAG indexing, and knowledge stewardship.
40
View repository →Go
MIT
