Grisoco AI security audits
Server Details
Smart-contract security audits for EVM chains and DAML: quote, run and fetch reports.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool maps to a distinct step in the audit lifecycle: quote (price), submit (charge and start), get_audit (status), get_audit_report (output), list_audits (history), get_balance (funds). The descriptions explicitly sequence get_audit before get_audit_report, removing the only potential overlap.
All six names follow a consistent verb_noun snake_case pattern (get_, list_, quote_, submit_), with get_audit/get_audit_report being a natural resource/sub-resource pair rather than an inconsistency.
Six tools is tightly scoped to the domain, and each one covers a step that an agent genuinely needs (price, submit, poll, fetch, list, balance), with no redundancy or filler.
The full lifecycle is covered end-to-end, including a safe dry-run pricing step and balance check. The only visible gap is the absence of a cancel/abort operation for a running or queued audit, plus top-up being delegated to an external dashboard.
Available Tools
6 toolsget_auditGet audit statusARead-onlyInspect
Status of an audit: queued, running, succeeded, failed (refunded) or expired.
Inputs: audit_id (required). Returns: id, error, stage, status, +14 more
get_audit_reportGet audit reportARead-onlyInspect
The finished report as Markdown (or the full JSON). Only once get_audit says succeeded.
Inputs: audit_id (required), format. Returns: format, report, audit_id
get_balanceGet balanceARead-onlyInspect
The account's prepaid balance in US cents. Top-ups are made in the Grisoco dashboard.
Inputs: no named parameters. Returns: currency, balance_cents
list_auditsList auditsCRead-onlyInspect
The account's most recent audits, newest first.
Inputs: limit. Returns: audits
quote_auditQuote an auditARead-onlyInspect
Price an audit without charging anything. Returns price_cents and whether the balance covers it.
Inputs: files (required), product (required), project_name (required), language, +1 more. Returns: product, affordable, price_cents, audit_targets, +4 more
submit_auditSubmit an auditAInspect
Start an audit. SPENDS the quoted price from the prepaid balance, refused (nothing charged) if the price is above max_price_cents. Returns an audit id at once; the audit runs in the background (minutes). Poll get_audit about every 30 seconds.
Inputs: files (required), product (required), project_name (required), max_price_cents (required), +2 more. Returns: id, error, stage, status, +14 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
EVM audit (Slither + source + security.txt + MCP-probe + wallet-exposure). 6 tools + /trace.
Read-only smart-contract security intelligence for autonomous agents.
AI smart contract security audits by Nethermind. Run scans and pull findings into your agent.
Smart-contract risk reports for AI agents on 20 EVM chains, paid per call via x402 ($0.02 USDC).
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceEnables static auditing of EVM Solidity smart contracts to detect critical vulnerabilities such as reentrancy state changes, unhandled external calls, unchecked delegatecall, and tx.origin authentication flaws, producing risk audit reports.-
- AlicenseAqualityCmaintenanceEnables static security audit of Solidity smart contracts by analyzing source code or deployed bytecode for vulnerabilities, providing risk scores and detailed findings.1MIT
- AlicenseAqualityDmaintenanceFetches verified EVM smart contract source code, scans for vulnerabilities, analyzes token holder distribution, and generates audit reports.5MIT
- FlicenseNot gradedqualityBmaintenanceEnables users to perform static security audits on EVM Solidity contract code for critical flaws such as reentrancy state changes, unhandled external calls, unchecked delegatecall, and tx.origin authentication vulnerabilities, returning risk audit reports.7-
Glama MCP Gateway
Add one secure layer between your agents and this server.