Skip to main content
Glama

Verify a tool, MCP server or package before invoking it

unfragile_verify
Read-only

Returns our verdict on a tool, MCP server or package (trusted · caution · unverified · flagged) and the reason, with its Ed25519-signed passport, checkable offline against https://unfragile.ai/api/v1/trust-passport-public-key. A flagged verdict means it failed our checks.

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": {
      "target": "<target>"
    },
    "name": "unfragile_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetYesTarget identity, e.g. 'npm:@stripe/mcp', a package name, or a record id

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with that: the passport is 'checkable offline' against a published public-key URL, so no open-world call is implied for verification. It adds real behavior beyond the annotations — the verdict taxonomy, the signed-passport artifact, the verification key location, and the meaning of 'flagged' (failed our checks). It stops short of saying what is returned for an unknown or untracked target.

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?

Two sentences, front-loaded with the returned value and its possible states, with the provenance detail following. Every clause carries information; the embedded URL and signature details make the second sentence dense but not wasteful.

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?

With no output schema, the description carries the return-value burden and does so: verdict, reason, and signed passport. It also explains how to verify the passport offline. Remaining gaps are minor — the distinctions among 'caution' and 'unverified', and behavior on an unrecognized target, are unstated.

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% and the single 'target' parameter already carries an example-format description. The description adds only the broad target categories ('tool, MCP server or package'), which loosely maps to the accepted identity forms but adds no syntax or format detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb and resource: returns a trust verdict (trusted · caution · unverified · flagged) plus reason and a signed passport for a tool, MCP server or package. The enumerated verdict values make the outcome concrete. It does not name or contrast itself with the siblings unfragile_find, unfragile_passport, or unfragile_resolve, so sibling differentiation is left to the title.

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?

The title supplies the key timing cue ('before invoking it'), which tells an agent this is a pre-flight trust check. The description body itself gives no when-to-use/when-not guidance and never routes the agent to the sibling tools that also deal with passports or lookups. Usage is implied rather than stated.

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.