Skip to main content
Glama

Tinplate Edge AI Safety, Security & EU Compliance

tinplate_ssrf_firewall

Read-onlyIdempotent

Agent URL & SSRF Signal Validator API: Flag untrusted URLs and redirect chains for SSRF signals (advisory pre-check, not a sandbox). (Endpoint: POST /v1/ssrf-firewall)

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": {
      "url": "<url>"
    },
    "name": "tinplate_ssrf_firewall"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesTarget URL to evaluate for SSRF risk.
check_dnsNoResolve A/AAAA records via DoH and check resolved IPs (default true).
inspect_redirectsNoFollow redirects via private fetcher to inspect redirect chain (default false; paid plans only).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / check_dns / default
      Added value: +true
    • addedInput schema / properties / inspect_redirects / default
      Added value: +false
    • changedInput schema / properties / inspect_redirects / description
      Previous value: -"Follow redirects via private fetcher to inspect redirect chain (default false)."New value: +"Follow redirects via private fetcher to inspect redirect chain (default false; paid plans only)."
  2. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed6 schema fields changed
    • addedInput schema / properties / check_dns
      Added value: +{
      +  "description": "Resolve A/AAAA records via DoH and check resolved IPs (default true).",
      +  "example": true,
      +  "type": "boolean"
      +}
    • addedInput schema / properties / inspect_redirects
      Added value: +{
      +  "description": "Follow redirects via private fetcher to inspect redirect chain (default false).",
      +  "example": false,
      +  "type": "boolean"
      +}
    • changedInput schema / properties / url / description
      Previous value: -"Parameter 'url' (e.g. \"http://169.254.169.254/latest/meta-data/iam/security-credent\")"New value: +"Target URL to evaluate for SSRF risk."
    • addedInput schema / properties / url / example
      Added value: +"https://example.com/docs"
    • addedInput schema / properties / url / maxLength
      Added value: +2048
    • addedInput schema / properties / url / minLength
      Added value: +1
  4. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds the meaningful caveat that results are advisory only, but says nothing about the response content, confidence level, or what happens with unresolvable DNS, which is the behavior an agent most needs.

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?

One compact sentence plus endpoint, front-loaded with the core action and immediately followed by the key scope caveat. No filler, though the endpoint string is of limited value to an agent that already has the tool binding.

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

Completeness3/5

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

With no output schema, the description should indicate what a 'signal' result looks like (finding list, risk verdict, chain details). It conveys scope and caveats but leaves the return shape and error behavior entirely unspecified for a three-parameter validator.

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%, with each of the three parameters documented including defaults and the paid-plan restriction on inspect_redirects. The description adds no parameter meaning beyond the schema, so the baseline of 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 specific verb and resource ('Flag untrusted URLs and redirect chains for SSRF signals') and names the analyzed artifacts (URLs, redirect chains). No sibling covers SSRF, so the resource itself differentiates it from the guard/scanner family.

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

Usage Guidelines3/5

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

'Advisory pre-check, not a sandbox' implies it should be called before fetching an untrusted URL, which gives usable positioning. There is no explicit when-not guidance (e.g., do not rely on it as the sole control) and no named alternative or fallback flow.

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