Skip to content
MCP server

Bounty Operator

Argue against a security finding or draft bug bounty report before you submit it

Install
Pricing
Freemium
Platforms
CLI, API, Web
Runs
Remotely
Version
0.9.23
Listing updated
3 days ago

About Bounty Operator

Bounty Operator is a freemium MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.

Bounty Operator reviews a report the way a skeptical triager would. The agent checks the finding against the code first, with 11 review types including code, Solidity and draft-report reviews.

There are two routes. Local tools prepare a review for your agent's own model with no account: prepare_review builds a manifest and instructions, run_gauntlet_plan lists the eight stages, and build_packet produces a verdict and evidence packet. Hosted run_review needs an account token and your own provider key, such as OpenRouter, and can run up to 15 minutes.

Setup is documented for Claude Code, Codex, Cursor and OpenCode, with long timeouts.

Install

Run in a terminal

claude mcp add --transport http bounty-operator https://bountyoperator.com/api/mcp

Add to Settings → Connectors → Add custom connector

https://bountyoperator.com/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "bounty-operator": {
      "url": "https://bountyoperator.com/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "bounty-operator": {
      "type": "http",
      "url": "https://bountyoperator.com/api/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "bounty-operator": {
      "serverUrl": "https://bountyoperator.com/api/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "bounty-operator": {
      "type": "http",
      "url": "https://bountyoperator.com/api/mcp"
    }
  }
}

Tools this server provides (5)

Read directly from the server.

list_profiles
Call first when you do not know which review fits. Returns every review profile with what it checks, what files it needs and whether it is hosted, the gauntlet stage order, the verdicts per mode, and the provider and model ids run_review accepts. A hosted profile runs through run_review; a core one also runs on your own model through prepare_review. No account needed.
prepare_review
Call before reviewing code or a draft report with your own model. Takes the core profiles: general, solidity, report. Scans the files for secrets, then returns a SHA-256 manifest, the reviewer instructions, the output format and the request to answer. File contents are not sent back. When the scan blocks, the result lists file, line and kind of each match. A hosted profile is refused with code hos
build_packet
Call after writing a review from prepare_review. Reads the review, checks every cited file and line against the manifest, and returns the verdict, the reference problems and the Markdown evidence packet with file hashes. No account needed.
account
Call before run_review to check the allowance. Returns the plan, the hosted reviews used today, the number that run at once and the time the allowance resets. Needs the connection token in the Authorization header.
run_review
Runs the review on the provider and model you name, using the key in the X-Provider-Key header, and returns the review, its verdict, the reference check, the manifest and the remaining allowance. Takes every profile and is the only way to run a hosted one. The verdict and panel profiles run on an Operator plan: a free account is refused with code operator_only and keeps its daily review. Uses one

What it does

11 review types
Code, Solidity, draft reports and more.
Account-free reviews
Three types run on your agent's own model.
Eight-stage gauntlet
Paid pre-submission run.
Evidence packet
Verdict and reference check.
Remote or local
Hosted endpoint or npx.
Panel review
Compare 2-4 models on paid plan.

Good for

  • Test a bug report
  • Check a Solidity finding
  • Prepare a pre-submission review
  • Simulate a triager

Pricing

Freemium, from $10 a month

Free; Operator US$10/month

Prices change. Check bountyoperator.com before you buy.

Bounty Operator FAQ

Free?

One hosted review a day on your own key.

Paid?

Operator is US$10 a month.

Timeouts?

Raise the client timeout to 20 minutes.

Is Bounty Operator free?

Bounty Operator has a free plan, with paid plans for more usage or features. Paid plans start at $10 a month.

How do I add Bounty Operator to Claude Code?

Run this command in your terminal: claude mcp add --transport http bounty-operator https://bountyoperator.com/api/mcp

What are the best alternatives to Bounty Operator?

The closest alternatives to Bounty Operator are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

Alternatives to Bounty Operator

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  3. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  4. Leash

    MCP server

    Review what your AI touched, approve risky actions and undo supported changes

    • 1 tool
    • Remote
    • Free
    • 1 GitHub star
    • Security
  5. SecureCloud

    MCP server

    SentinelOne and IT security catalog, prices, quotes and checkout links for Israel

    • 7 tools
    • Remote
    • Free
    • Security