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 operant-mcp MCP server?
Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.
How to install operant-mcp
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": {
"operant-mcp": {
"command": "npx",
"args": [
"-y",
"saagar-operant-mcp"
]
}
}
}Related MCP servers
SA

Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
0
View repository →TypeScript
MIT
SH

shadow-mcp
Active
Local MCP server that inventories and risk-grades MCP servers configured on this machine.
0
View repository →Python
MC

mcp-audit
Active
Scan, enumerate, and risk-score every MCP server configured on your machine.
4
View repository →Python
MIT
MC

mcp-trust
Active
Check the danger grade of any public MCP server before you connect.
0
View repository →Python
MIT
JU

junai Pipeline MCP
Active
Agentic pipeline orchestration MCP server for AI-driven development workflows.
0
View repository →Python
SA

Sable Platform + HyperDX Observability
Maintained
Manage Sable AI voice agents, query HyperDX logs and metrics, and deploy — all from your IDE
0
View repository →Go