Bounty Operator MCP server
Commit Nov 15, 2026Helps security researchers strengthen bug bounty reports by scanning for secrets, verifying evidence, and simulating triager reviews.
Also known as bountyoperator/bounty-operator, bounty-operator
- Stars
- 6
- Tools
- 6
- Downloads, 30 days
- —
- Latest version
- 0.9.23
- Last commit
- Nov 15, 2026
- License
- MIT
What is Bounty Operator MCP?
Bounty Operator helps security researchers strengthen bug bounty reports by scanning for secrets, verifying evidence, and simulating triager reviews. It exposes 6 tools, such as list_profiles, prepare_review, run_gauntlet_plan.
Summary generated from the project's README
About Bounty Operator MCP server
Security researchers can strengthen bug bounty reports by using this server to scan for secrets, verify evidence, and simulate triager reviews. It helps users catch missing evidence and clarify impact before submitting findings to a program. The server supports core profiles like general code security, Solidity reviews, and report challenges that run locally using the agent's own model without requiring an account or API keys.
For more advanced analysis, the server provides access to hosted profiles such as triage, severity, and provenance through the run_review tool. These hosted stages require a connection token and a provider key for services like OpenRouter, Anthropic, or OpenAI. Users can set up the server as a remote endpoint for clients like Claude Code, Codex, and Cursor, or run it locally via npx to keep review preparation on their own machine. The system includes a privacy check that scans files for secrets or sensitive information like IP addresses before processing.
What you can do with it
- 1Automate the gauntlet processDevelopers can run a finding through eight sequential stages to receive a final submission verdict.
- 2Validate draft bug reportsUsers can check every claim in a draft report against the actual source code to build an evidence packet.
- 3Prevent accidental secret leakageThe server automatically scans files for sensitive data like emails or IP addresses before sending them to a provider.
Written from the project's README. Every use case is checked against a quote from it.
How to install Bounty Operator MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Bounty Operator MCP in Claude Code
$ claude mcp add --transport http bounty-operator https://bountyoperator.com/api/mcpInstall Bounty Operator MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"bounty-operator": {
"url": "https://bountyoperator.com/api/mcp"
}
}
}Install Bounty Operator MCP in VS Code
.vscode/mcp.json
{
"servers": {
"bounty-operator": {
"type": "http",
"url": "https://bountyoperator.com/api/mcp"
}
}
}Install Bounty Operator MCP in VS Code CLI
$ code --add-mcp '{"name":"bounty-operator","type":"http","url":"https://bountyoperator.com/api/mcp"}'Install Bounty Operator MCP in Codex
$ codex mcp add bounty-operator --url https://bountyoperator.com/api/mcpInstall Bounty Operator MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.bounty-operator] url = "https://bountyoperator.com/api/mcp"
Install Bounty Operator MCP in Gemini CLI
$ gemini mcp add -s user --transport http bounty-operator https://bountyoperator.com/api/mcpInstall Bounty Operator MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"bounty-operator": {
"url": "https://bountyoperator.com/api/mcp",
"type": "http"
}
}
}Bounty Operator MCP tools 6
Detected from the READMElist_profilesprepare_reviewrun_gauntlet_planbuild_packetaccountrun_review
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablebountyoperator/bounty-operator is public and reachablegithub.com/bountyoperator/bounty-operator ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/bountyoperator/bounty-operator ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 284 msPass
README
View on GitHubBounty Operator MCP
Make your strongest case before you submit.
Check your proof, make the impact explicit, and catch missing evidence before the triager has to ask.
This is the MCP server for Bounty Operator. Your agent names the files, the server scans them for secrets and returns the review request, your agent's own model writes the review, and the server checks every cited line and builds the evidence packet. Preparing a review and building the packet need no account and no key.
That route covers the three core profiles. Every other profile, and seven of the eight gauntlet stages, runs as a hosted review on the Bounty Operator service with your own provider key.
Install
Two routes. Both work today.
Remote endpoint
Nothing to install. One line per client.
Claude Code
claude mcp add --transport http bounty-operator https://bountyoperator.com/api/mcp
Codex
codex mcp add bounty-operator --url https://bountyoperator.com/api/mcp
Cursor, in ~/.cursor/mcp.json or .cursor/mcp.json in a project:
{ "mcpServers": { "bounty-operator": { "url": "https://bountyoperator.com/api/mcp" } } }
Local server
This package. It reads files by path, keeps review preparation on your machine and adds run_gauntlet_plan. Node 22 or later, no dependencies. npx installs it from the tarball the site serves.
Claude Code
claude mcp add --transport stdio bounty-operator -- npx -y https://bountyoperator.com/dl/bounty-operator-mcp.tgz
Codex
codex mcp add bounty-operator -- npx -y https://bountyoperator.com/dl/bounty-operator-mcp.tgz
Cursor, in ~/.cursor/mcp.json or .cursor/mcp.json in a project:
{ "mcpServers": { "bounty-operator": { "command": "npx", "args": ["-y", "https://bountyoperator.com/dl/bounty-operator-mcp.tgz"] } } }
Any other client: command npx, arguments -y https://bountyoperator.com/dl/bounty-operator-mcp.tgz, transport stdio.
On Windows outside WSL, Claude Code starts npx through cmd: end the command with -- cmd /c npx -y https://bountyoperator.com/dl/bounty-operator-mcp.tgz.
The package is coming to npm as bounty-operator-mcp. Until it is published, the tarball URL above is the install.
A first request to try:
Use bounty-operator to prepare a Solidity review of src/Vault.sol. Answer the request it returns, then build the packet.
Tools
| Tool | Call it | It returns | Needs |
|---|---|---|---|
list_profiles |
When you do not know which review fits | The review profiles, each with hosted true or false, the gauntlet order, the verdicts, the providers and models |
Nothing |
prepare_review |
Before reviewing code or a draft report with your own model | For a core profile: SHA-256 manifest, privacy findings, reviewer instructions, output format, the request to answer | Nothing |
run_gauntlet_plan |
For the full pre-submission run | The eight stages in order with the tool that runs each, the Context fields still empty, the call that ends the run | Nothing |
build_packet |
After writing the review | Verdict, reference check, the Markdown evidence packet | Nothing |
account |
Before a hosted review | Plan, reviews used today, reset time | Token |
run_review |
To run a review on a provider's model | The review, its verdict, the reference check, the remaining allowance | Token and provider key |
Six tools here, five on the remote endpoint: run_gauntlet_plan is local only.
Limits per call: 50 files, 120 KB per file, 240 KB and 20,000 lines in total.
Core and hosted profiles
prepare_review takes the three core profiles: general (Code security review), solidity (Solidity review) and report (Challenge a draft report). Their method is in this package and your agent's own model answers the request.
Every other profile is hosted: scope, provenance, prior-art, poc, severity, triage, report-edit and scanner. Each runs on the Bounty Operator service through run_review, on your own provider key. The method of a hosted profile is added on the service. It is not in this package and no tool returns it.
For a hosted profile:
list_profilesreturns it withhosted: true.prepare_reviewfails with the codehosted_profilebefore any file is read.run_reviewruns it and uses one hosted review. A review the provider blocks under its usage policy is not counted. The two profiles no list shows,verdictandpanel, are the last step of the gauntlet and of a panel review: they run on Operator only.
{
"profile": "triage",
"error": "Triager simulation runs on the server. Call run_review with profile \"triage\": it needs BOUNTY_OPERATOR_TOKEN and the provider key in this server's environment.",
"code": "hosted_profile"
}
Files by path
prepare_review and run_review take paths, files, or both.
pathsare read by the server from its working directory:["report.md", "src/Vault.sol"]. The agent does not have to send the file text.filescarry the text inline:[{ "name": "src/Vault.sol", "content": "..." }].
A path resolves under the working directory and nowhere else. The server refuses .., an absolute path outside the directory, and a link that leaves it. File contents go to the review and are never returned: a result holds the label, size, line count and SHA-256 of each file.
A client that starts the server outside your project sets BOUNTY_OPERATOR_ROOT to the project folder.
The privacy check
Every call scans the files first. A secret blocks the call and the result lists file, line and kind of each match, never the matched text. An email or IP address stops the call until you repeat it with acknowledgeWarnings: true. run_review runs this check on your machine before anything is sent.
Prompts
Three prompts, listed by clients that support them as slash commands:
| Prompt | What it does |
|---|---|
challenge-report |
Checks every claim in a draft report against the code it cites, then builds the packet |
solidity-review |
Maps entry points and invariants in the contracts you name |
gauntlet |
Takes a finding through the eight stages in order and ends with one verdict |
In Claude Code: /mcp__bounty-operator__gauntlet.
The gauntlet
Eight stages, in the order that ends a weak report early: scope, provenance, prior art, proof, severity, triager, report, verdict. run_gauntlet_plan returns the plan and names the tool that runs each stage. Seven stages are hosted and run through run_review, so the run needs a connection token and a provider key. The report stage is a core profile: prepare_review returns its request and your agent's own model answers it. Each review is passed forward as stage-<n>-<profile>.md, and the run ends with build_packet. The verdict is one of submit, rewrite-then-submit, prove-first, hold-duplicate, drop.
A run uses seven hosted reviews. Free covers one hosted review per UTC day, so a full run takes Operator. The plan carries the count under hosted, and account returns the allowance before the run starts.
Hosted reviews
run_review runs any profile on a provider's model with your own API key and returns the review checked. It is the only way to run a hosted profile from an agent. It uses the same allowance as the website: one hosted review per UTC day on Free, any profile, and unlimited on Operator at US$10 per month.
Three result fields say when the text is not a review. truncated is true when the provider cut the answer short. refused is true when the model or the provider declined. blocked is set when the review was blocked: anthropic-cyber, anthropic-reasoning or openai-cyber for that provider's safeguards, guardrail for a guardrail on the key or its account, policy for any other block under a usage policy. A blocked review is never counted. After a refusal or a block, do not call again with the same model: use another model or provider, or prepare_review for a core profile.
- Sign in at bountyoperator.com and create a connection in the account panel. The token starts with
bok_and is shown once. - Start the server with the token and one provider key in its environment.
claude mcp add --transport stdio --env BOUNTY_OPERATOR_TOKEN=bok_... --env OPENROUTER_API_KEY=sk-or-... bounty-operator -- npx -y https://bountyoperator.com/dl/bounty-operator-mcp.tgz
Codex, in ~/.codex/config.toml:
[mcp_servers.bounty-operator]
command = "npx"
args = ["-y", "https://bountyoperator.com/dl/bounty-operator-mcp.tgz"]
env_vars = ["BOUNTY_OPERATOR_TOKEN", "OPENROUTER_API_KEY"]
tool_timeout_sec = 1200
A hosted review ends within 270 seconds. On a Bounty Operator model it runs for up to 15 minutes: the first request after a quiet spell can wait up to 10 minutes for the model to start, and the progress message says so while it does. Codex stops a tool call after 60 seconds by default, so keep the tool_timeout_sec line.
The token and the key are read from the environment. Neither is a tool argument, and both are removed from every result.
The remote endpoint takes the same two values as headers: Authorization: Bearer <token> and X-Provider-Key: <key>. The commands for each client are at bountyoperator.com/mcp.
For Novita AI, set NOVITA_API_KEY locally (and include it in Codex's env_vars) and call run_review with "provider": "novita". Create a key at Novita Key Management. The default is deepseek/deepseek-v4.1-flash; zai-org/glm-5.3-flash is also listed. Both local and remote list_profiles expose the provider and its models. On the remote endpoint, pass the Novita key in X-Provider-Key, not as a tool argument. Novita bills model usage separately; selecting it does not change the app's default provider or enable a fallback. Signup attribution is never sent with inference requests.
For Nebius Token Factory, set NEBIUS_API_KEY locally (and include it in Codex's env_vars) and call run_review with "provider": "nebius". Create a key at Nebius Token Factory. The default is deepseek-ai/DeepSeek-V4.1-Flash; zai-org/GLM-5.3-Flash and moonshotai/Kimi-K3 are also listed. Requests ask Nebius not to store the answer. On the remote endpoint, pass the Nebius key in X-Provider-Key, not as a tool argument. Nebius bills model usage separately; selecting it does not change the app's default provider or enable a fallback.
Environment
| Variable | Purpose |
|---|---|
BOUNTY_OPERATOR_TOKEN |
Connection token for account and run_review |
BOUNTY_OPERATOR_MODEL |
Model id run_review uses when the call names none |
BOUNTY_OPERATOR_ROOT |
Absolute path of the project folder that paths resolve under. Default: the working directory |
OPENROUTER_API_KEY, ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, XAI_API_KEY, DEEPSEEK_API_KEY, MISTRAL_API_KEY, GROQ_API_KEY, NOVITA_API_KEY, NEBIUS_API_KEY, INFRON_API_KEY, ORCAROUTER_API_KEY, BOUNTYOPERATOR_API_KEY |
Provider key for run_review, one per provider |
What the server reaches
list_profiles,prepare_review,run_gauntlet_planandbuild_packetrun on your machine with no network call.accountandrun_reviewcallhttps://bountyoperator.comwith your token.run_reviewsends the files and your provider key. The service adds the method of the profile, passes the request and the key to the provider for that one request and returns the review. It stores no files, keys or review text.- The server reads the files you name under the working directory. It writes nothing to disk and runs no code from the files.
When a call fails
A failed call returns isError with one JSON object: error, a sentence the agent can act on, and code.
| Code | Meaning |
|---|---|
hosted_profile |
prepare_review was called with a hosted profile. Nothing was read or counted. Call run_review. |
privacy_block |
The privacy check found a secret. The result lists file, line and kind. |
privacy_warn |
The privacy check found an email or IP address. Repeat the call with acknowledgeWarnings: true to send the files as they are. |
token |
BOUNTY_OPERATOR_TOKEN is missing, malformed, expired or revoked. |
daily_used |
The free review of the day is used. The result carries resetsAt. |
operator_only |
run_review was called with verdict or panel on an account without Operator. Nothing was sent to the provider and the review of the day is not used. |
review_running |
The account is running as many reviews as its plan allows. |
provider |
The provider rejected the key or the model, had no credit, failed or timed out. The review is not counted. |
provider_policy |
The provider blocked the request under its usage policy. The key is not the cause and the review is not counted. Call again with another model or provider, not the same one. |
output_withheld |
The model repeated its instructions instead of reviewing, so the answer was stopped and the call used one review. Run it again or choose a stronger model. |
bad_path, bad_root |
A path cannot be read under the working directory, or the working directory itself cannot be used. |
network, timeout, cancelled |
The service was not reached or the connection closed before the answer, the service did not answer within 300 seconds (960 for a review on a Bounty Operator model), or the client cancelled the call. |
Verify the download
The tarball on the site is listed with its SHA-256 at https://bountyoperator.com/dl/SHA256SUMS.txt.
curl -sO https://bountyoperator.com/dl/bounty-operator-mcp-0.9.18.tgz
curl -s https://bountyoperator.com/dl/SHA256SUMS.txt | sha256sum -c --ignore-missing
npx -y file:$PWD/bounty-operator-mcp-0.9.18.tgz --version
Start a downloaded tarball with the file: prefix and its absolute path. npm reads a bare path as a command to run.
Develop
The review engine lives in web/public of the repository and is copied into lib/ before every test and pack.
npm install
npm test
node ../scripts/build-mcp.mjs
build-mcp.mjs packs the tarball, checks its contents against a whitelist, installs it into an empty folder, completes an MCP handshake and writes web/public/dl/.
Source: github.com/bountyoperator/bounty-operator. MIT licence.
Bounty Operator MCP questions
How do I add Bounty Operator MCP to Claude Code?
Run claude mcp add --transport http bounty-operator https://bountyoperator.com/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Bounty Operator MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Bounty Operator MCP provide?
It exposes 6 tools, including list_profiles, prepare_review, run_gauntlet_plan, build_packet, account.
Do I need an account to prepare a review?
No, preparing a review and building the evidence packet requires no account and no key.
How does the server handle sensitive information in files?
The server scans files for secrets before any call; if a secret is found, the call is blocked and the server returns the file, line, and kind of match without returning the actual text.
Can I run reviews on my own AI models?
Yes, core profiles like Solidity reviews or report challenges allow your agent's own model to answer the review request locally.
What are the file size limits for the server?
The server supports up to 50 files, with a limit of 120 KB per file and a total limit of 240 KB or 20,000 lines.