Pugi

Check a GitHub repository for security issues

scan_repo

DestructiveIdempotent

Use this when the person wants a public GitHub repository checked for leaked secrets, vulnerable or malicious dependencies and risky code. No code is run. 3 free checks a day per account, then $1 when the check finishes; a failed check costs nothing. Do not use for websites (use scan_url) or private repositories.

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": {
      "repo_url": "<repo_url>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "scan_repo"
  }
}

Input Schema

Name	Required	Description
`ref`	No	Optional branch name. Default: the repository's default branch.
`language`	No	The language the person is writing in, as a BCP 47 tag such as "ru".
`repo_url`	Yes	A public GitHub repository, for example https://github.com/owner/repo
`idempotency_key`	Yes	A unique string naming this check. Reuse it to collect the result or to retry; the same key is never charged twice.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

addedInput schema / properties / language

Added value: +{
+  "description": "The language the person is writing in, as a BCP 47 tag such as \"ru\".",
+  "maxLength": 35,
+  "pattern": "^[a-z]{2,3}(-[A-Za-z0-9]{2,8})?$",
+  "type": "string"
+}

AddedOct 24, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Adds context the annotations cannot express: no code is executed, 3 free checks per day per account, $1 charged only when a check finishes, failed checks are free. This complements destructiveHint/idempotentHint rather than restating them. It stops short of saying the check is asynchronous and that results are collected via job_status, which is the main behavioral gap.

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?

Four short sentences, each carrying distinct information: trigger, scope, safety, cost, exclusions. Exclusions are placed last where they act as a final routing guard, and nothing is padded.

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

Completeness4/5

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

Covers trigger, scope, cost model, and non-goals for a paid, open-world scan. The one missing piece is how a result is retrieved (the idempotency key plus job_status sibling imply an async collect step the description never mentions), which matters for correct multi-call use.

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 description coverage is 100%, so the schema already carries branch, language tag, URL format, and idempotency semantics. The description adds nothing parameter-specific beyond pricing implications, so the baseline 3 applies.

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 concrete verb and resource (check a public GitHub repository) plus the exact scope of the check (leaked secrets, vulnerable/malicious dependencies, risky code). It explicitly distinguishes itself from scan_url, so an agent can route without opening either schema.

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

Usage Guidelines5/5

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

Opens with a direct trigger ('Use this when the person wants...') and names two exclusions with the alternative for one of them (websites → scan_url) and a hard limit for the other (no private repositories). Little is left to inference.

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

All Pugi tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?