bug-bounty-intelligence-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_contractA | Submit a public GitHub repository for an automated smart contract security analysis. Runs the Al-Mizaan v3 7-gate framework (code, reachability, threat-model, invariant, protocol-intent, impact, formal proof) to filter out false positives before reporting anything — on a real benchmark run (3FLabs/grunt, 218 contracts) plain Slither reported 27 "High" findings with a 100% false-positive rate; see BENCHMARK.md for the full comparison. Pattern awareness is drawn from a corpus of 27,681 submitted Sherlock/Code4rena findings; the acceptance-rate numbers used elsewhere in this server (list_vulnerability_patterns) are limited to the 1,032 findings that could be exact-reconciled against contest outcomes — see METHODOLOGY.md. Cost: $5 USDC on Base (eip155:8453) via x402. Delivery is guaranteed within 24h — the sample run documented in README.md took about 25 minutes. Returns a job_id. Use get_scan_report to poll for results. If payment_required is true, pay $5 USDC to the payTo address on Base, then retry scan_contract with the same repo_url. |
| get_scan_reportA | Poll the status of a job_id returned by scan_contract. Call this every minute or two after submitting — real runs have taken around 25 minutes, delivery is guaranteed within 24h, so polling faster than that just re-checks a job that is still processing. Returns status (queued/processing/complete), the repo under scan, and — once complete — reportUrl (the full Al-Mizaan-validated findings report) and findingsCount. A 404 means the job_id does not exist — double-check what scan_contract actually returned rather than retrying blindly. |
| list_vulnerability_patternsA | Returns historical vulnerability patterns and acceptance rates from Sherlock audit-competition findings. Numbers are limited to contests where results could be exactly reconciled against Sherlock's own published outcomes (1,032 findings across 10 contests) — no estimated or unverifiable figures. Useful for understanding what types of bugs are most likely to be valid in a given protocol type. This tool is FREE — no payment required. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct role: list_vulnerability_patterns provides historical data, scan_contract starts a new analysis, and get_scan_report polls for results. There is no ambiguity or overlap between them.
All tool names follow a consistent verb_noun snake_case pattern: list_vulnerability_patterns, scan_contract, and get_scan_report. The naming clearly communicates the action and resource.
With only 3 tools the server feels slightly minimal, but the count is appropriate for a focused scan-and-report workflow. Each tool serves a distinct step in the user journey, so the size is reasonable rather than inadequate.
The server covers the full lifecycle from querying historical patterns to submitting a scan and retrieving the report. A minor gap is the lack of a way to list past jobs or cancel a scan, but this is not essential for the core purpose.