Skip to main content
Glama

Check a coding agent's guard settings

check_agent_setup
Read-onlyIdempotent

Check whether a coding agent's own guard settings hold, against runs the Durability Curve measured with its paid kits: Claude Code permission rules (which of 30 spellings of deleting a remote branch, force-pushing or pushing to main they let through), sandbox and bypass settings, prompt-injection exposure (WebFetch, shell network access), hook wiring and exit codes, and skill frontmatter; Cursor CLI cli.json rules; Codex config.toml sandbox mode. Send the files' text, with every env block, token, header and key removed. Returns findings, most severe first, each with what it is based on, the measured run (tool, version, date, setup, result) and the kit that tests it on this machine. Free: the counts, the first finding in full and the titles of the rest. Paid: every finding with its fix and the configuration that held. The guard check reads only the text it is sent and runs nothing. Each finding says whether it was predicted from the user's rules, read from their config or taken from the docs, and names the measured run behind it. It is not a security audit, and no finding does not mean a guard holds: only running the kit on the machine shows that.

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": {
      "files": "<files>"
    },
    "name": "check_agent_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesYesThe agent configuration files to check, up to 12, under 60,000 characters in all.
versionsNoThe tool versions, from claude --version, cursor-agent --version or codex --version, so findings can say whether the measured version matches yours.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent, closed-world, and the description still adds real substance: the check reads only the text it is sent and executes nothing, findings are returned most-severe-first with their evidentiary basis, and the free tier yields counts, the first finding and titles only. The confidence-provenance note (predicted from rules vs read from config vs taken from docs) is behavior an agent could not infer from structured fields.

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

Conciseness3/5

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

Front-loaded with purpose, but the opening sentence is a ~100-word run-on built from semicolons and colons, and the evidence-provenance point is made twice (once as 'what it is based on, the measured run' and again as 'predicted from the user's rules, read from their config or taken from the docs'). Dense but readable; tightening would help.

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?

There is no output schema, so the description carries the burden of describing returns — and it does: findings, severity ordering, the evidence attached to each, the free/paid split, and the escape hatch about running the kit. For a two-parameter tool with full schema coverage and rich annotations, nothing an agent needs in order to call it correctly is missing.

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; the description earns a point by naming which configuration ecosystems and file shapes are actually understood, which tells the caller what is worth sending. It also reinforces the mandatory redaction of env blocks, tokens, headers and keys, though that largely restates the schema.

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 — checking a coding agent's guard settings against measured runs — and enumerates the exact surfaces it inspects (Claude Code permission rules, sandbox/bypass settings, prompt-injection exposure, hook wiring, Cursor cli.json, Codex config.toml). That level of specificity makes it unmistakable against siblings like search or get_kit.

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?

Gives clear conditions on when to call it (send the configuration text, redacted) and an explicit negative boundary: it is not a security audit, and absence of findings does not prove a guard holds — only running the kit on the machine does. It does not explicitly name the sibling tool that runs the kit, so the routing is implied rather than spelled out.

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