Grisoco AI security audits

Submit an audit

submit_audit

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.

Input Schema

Name	Required	Description	Default
`files`	Yes	Source files. path is relative (e.g. src/Vault.sol); imported files must be included too.
`product`	Yes	deep_review: AI security review on top of the analysis tools (Solidity or DAML). tools: static analysis tools only (Solidity), cheaper and faster.
`language`	No	Source language: solidity for EVM contracts, daml for Canton/DAML packages.	solidity
`project_name`	Yes	Project or company name shown on the report.
`audit_targets`	No	Optional: which files to audit and bill for. Default: every file sent. Imports are free.
`max_price_cents`	Yes	The most you agree to pay, in US cents. Use the price from quote_audit.

Output Schema

Name	Required	Description
`id`	Yes	Audit id.
`error`	Yes	Why the audit failed, if it did.
`stage`	Yes	Progress detail while running.
`status`	Yes	failed audits are refunded; expired reports were deleted after the retention window.
`product`	Yes	deep_review or tools.
`language`	Yes	solidity or daml.
`refunded`	Yes	True when the audit failed and the price was returned.
`total_loc`	Yes	Lines of code audited.
`created_at`	Yes	ISO 8601 timestamp.
`started_at`	Yes	ISO 8601 timestamp.
`finished_at`	Yes	ISO 8601 timestamp.
`price_cents`	Yes	Price charged, in US cents.
`project_name`	Yes	Project name shown on the report.
`audit_targets`	Yes	The files audited.
`contract_count`	Yes	Number of files audited and billed.
`discount_percent`	Yes	Account discount applied, 0 if none.
`report_available`	Yes	True when get_audit_report can return the report.
`report_expires_at`	Yes	When the report is deleted (ISO 8601).

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=false / idempotentHint=false; the description adds the critical context of what actually happens: a prepaid-balance spend, atomic refusal with nothing charged when the price exceeds max_price_cents, an immediate id return, and a background job taking minutes. This is materially more than the annotations convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and the spend implication, then async behavior and polling cadence. No filler; every sentence carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a non-idempotent, cost-incurring, asynchronous submission tool, the description covers cost, atomicity of failure, return shape at a high level, duration, and follow-up polling. With an output schema present, return-value details are appropriately left out.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so per-parameter meaning is already documented, including the enum options and file semantics. The description adds the guardrail semantics of max_price_cents (refusal behavior) but leaves other parameters, such as audit_targets and language, entirely to the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Start an audit') and immediately distinguishes this submission tool from its siblings by naming the price source (quote_audit) and the polling target (get_audit). An agent can position it in the workflow without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Establishes the workflow context – quoted price from quote_audit and polling get_audit every ~30 seconds – which implies the correct call order. It stops short of an explicit 'call quote_audit first' instruction or any when-not-to-use condition, so it is clear but not fully prescriptive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Grisoco AI security audits tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?