agentmods.dev

operant-mcp

A local, read-only MCP server for the OPERANT benchmark, a test suite used to measure and calibrate AI operating agents.

In plain words
What is it for?
Use it when running or inspecting OPERANT benchmark tasks through a locally installed MCP server.
Why use it?
It gives an agent access to the benchmark without allowing it to change data or perform write operations.

MCP server for Claude CodeCodexCursor

0 2d ago A scan tokens not measured original MIT
View the source file saagpatel/operant
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/saagpatel/operant/operant-mcp
Clone the repo
git clone --depth 1 https://github.com/saagpatel/operant

Made for: Claude Code, Codex, Cursor.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

operant-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

mcp/server.json · 10 lines

What it actually says

{
  "operant-mcp": {
    "command": "npx",
    "args": [
      "-y",
      "saagar-operant-mcp"
    ],
    "env": {}
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 10 lines scan A 920b159c351f

Subscribe to this mod's changes

operant-mcp is an MCP server published in the GitHub repository saagpatel/operant (0 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

AI SafetyBuilding agentsPrompt InjectionTestingagent-evaluationai-agentsllm-benchmark
Related

Other mcp servers, from other repositories

sentinel-ai

MCP server "sentinel-ai" as configured in MaxwellCalkin/sentinel-ai. Runs sentinel.mcp_server with python.

MaxwellCalkin/sentinel-ai · not measured

agentscore-mcp

Trust scoring for AI agents. Investigate, verify, and compare agent trustworthiness through MCP. Runs locally from the agentscore-mcp npm package.

tmishra-sp/agentscore-mcp · not measured

skillguard

MCP server "skillguard" as configured in epistemedeus/skillguard. Launched with epistemedeus/skillguard.

epistemedeus/skillguard · not measured

mcp

Authorize consequential AI agent actions before execution. Runs locally from the @decionis/mcp npm package. Needs 1 environment variable to run.

decionis/agent-safe-pipeline · not measured

agentgate

Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve. Runs locally from the @agentkitai/agentgate-mcp npm package.

agentkitai/agentgate · not measured

gnt

Git-native policy layer for AI agents: checkaction verdicts against rules approved via PR. Remote server at api.gntai.dev.

gnt-ai/gnt · not measured