Skip to main content
Glama

security_review

Idempotent

On-demand LLM security review of a project's deployed functions. Returns a structured Markdown report — findings (one per real risk), severity, and a fix.

Every plan can request a review. Paid plans get a longer report. Eligible paid plans also review when a preview is promoted. All plans use the same review model and minimal reasoning; only the report length limit differs.

Advisory only — never blocks anything. The deploy path never blocks on a pattern scan; it surfaces hits as warnings, and this tool is how you get the deep dive.

project_id is required (returns VALIDATION_ERROR if omitted). Backend failures are distinguishable, so a retry is never wasted on a persistent failure: a transient outage returns UPSTREAM_DOWN / UPSTREAM_RATE_LIMITED (retryable), while a persistent platform problem returns UPSTREAM_ERROR / CONFIG_ERROR (not retryable — a retry loop does not clear it).

Example:

{ "project_id": "my-saas" }
// Returns: { "findings": "## Findings\n### Auth bypass at api/checkout.ts ...\n...", "review_depth": "standard", "tier_unlocks_deep_review": false, ... }

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>"
    },
    "name": "security_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
focusNoOptional area to focus the review on (e.g. "the new payments flow", "auth changes since last week"). Up to 500 chars.
project_idYesProject ID (UUID), subdomain, slug, or 'default'. Resolved server-side.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations it discloses substantially more: the tool is strictly advisory and never blocks anything, report depth varies by plan tier, missing project_id yields VALIDATION_ERROR, and failure modes are split into retryable (UPSTREAM_DOWN / UPSTREAM_RATE_LIMITED) versus persistent (UPSTREAM_ERROR / CONFIG_ERROR). That retry-guidance is exactly the kind of behavior an agent cannot infer from readOnlyHint=false / idempotentHint=true / destructiveHint=false, and nothing in the text contradicts those hints.

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

Conciseness4/5

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

Front-loaded with purpose and output shape, then plan/tier expectations, then error semantics, then a compact example — a sensible progression. There is minor redundancy between 'never blocks anything' and 'The deploy path never blocks on a pattern scan', and the plan-tier paragraph is more expectation-setting than invocation guidance, but nothing is padding.

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?

No output schema exists, yet the description explains the returned report structure and the example surfaces fields like review_depth and tier_unlocks_deep_review, so return-value expectations are covered. Combined with tier behavior, retry semantics, and the advisory-only framing, an agent has everything needed to call this correctly and interpret failures.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning on top: it states project_id is required, notes that a UUID, subdomain, slug, or 'default' is resolved server-side, and specifies the VALIDATION_ERROR consequence of omission. The optional focus parameter is left entirely to the schema, which is acceptable given full coverage.

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

Purpose4/5

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

The description names a specific verb and resource — an LLM security review of a project's deployed functions — and states the output shape (Markdown report with findings, severity, and a fix). An agent can tell what it produces without opening the schema. It does not explicitly differentiate itself from the similarly-named security_sitekey sibling, so it stops short of a 5.

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?

It gives real usage context: on-demand invocation, available on every plan, and framed as the 'deep dive' that complements the warning-only pattern scan on the deploy path. That tells an agent when this is the right escalation. It doesn't name an explicit alternative tool or state when not to call it, so it isn't a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources