Skip to main content
Glama

veritas-8183-agent-notary-witness

check_mcp_server_trust

Read-only

[Private query, public score] Is this MCP server safe to connect? FREE, no signup: pass any public MCP serverUrl (or call with {} for a free sample preview) to report permissions, risky tools, prompt-injection signs and changes since the last check. Example: serverUrl='https://example.com/mcp'.

Input Schema

NameRequiredDescriptionDefault
serverUrlNoPublic https URL of the MCP server to check. Omit to see the free sample preview.
paymentTxHashNoOptional. Base USDC tx hash: 0.02 USDC = extra check after 5 free/day, 0.25 USDC = full 7-question dossier with Ed25519 seal.
paymentRecoveryTokenNoRequired with paymentTxHash. Generate a private random 32-byte token as 64 hex characters before the first paid request. Reuse it with the same transaction and server URL to retry or retrieve the report without paying again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / dependentRequired / paymentTxHash
      Previous value: -[
      -  "paymentRecoveryToken"
      -]New value: +[
      +  "serverUrl",
      +  "paymentRecoveryToken"
      +]
    • changedInput schema / properties / paymentTxHash / description
      Previous value: -"Optional. Base USDC tx hash: 0.02 USDC = extra check after 5 free/day, 0.25 USDC = full 7-question dossier with HMAC seal."New value: +"Optional. Base USDC tx hash: 0.02 USDC = extra check after 5 free/day, 0.25 USDC = full 7-question dossier with Ed25519 seal."
    • changedInput schema / properties / serverUrl / description
      Previous value: -"Public https URL of the MCP server to check."New value: +"Public https URL of the MCP server to check. Omit to see the free sample preview."
    • removedInput schema / required
      Removed value: -[
      -  "serverUrl"
      -]
  2. Changed3 schema fields changed
    • addedInput schema / dependentRequired
      Added value: +{
      +  "paymentTxHash": [
      +    "paymentRecoveryToken"
      +  ]
      +}
    • addedInput schema / properties / paymentRecoveryToken
      Added value: +{
      +  "description": "Required with paymentTxHash. Generate a private random 32-byte token as 64 hex characters before the first paid request. Reuse it with the same transaction and server URL to retry or retrieve the report without paying again.",
      +  "pattern": "^[a-fA-F0-9]{64}$",
      +  "type": "string"
      +}
    • changedInput schema / properties / paymentTxHash / description
      Previous value: -"Optional. Base USDC tx hash: 0.02 USDC = extra check after 5 free/day, 0.25 USDC = full signed 7-question dossier."New value: +"Optional. Base USDC tx hash: 0.02 USDC = extra check after 5 free/day, 0.25 USDC = full 7-question dossier with HMAC seal."
  3. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false and idempotentHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: "[Private query, public score]" discloses that the query is not published while the score is, and "changes since the last check" explains the non-idempotent comparison behavior. It omits rate limits and paid-tier thresholds, which appear only in the schema, so it is additive but not rich.

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?

The core question is front-loaded, followed by the report contents and one usage example in a single effective sentence. The bracketed tag and "FREE, no signup:" phrasing lean promotional, but they do carry privacy and pricing information, so they roughly earn their place.

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?

There is no output schema, so the description carries the burden of saying what comes back, and it does so by listing permissions, risky tools, prompt-injection indicators and change history. Combined with 100% schema coverage of the optional payment parameters, an agent has enough to call this correctly; only latency, report format and free-tier limits are unstated in the description body.

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 all three parameters (serverUrl, paymentTxHash, paymentRecoveryToken) are already documented in structured form, including the USDC pricing tiers and dependentRequired constraint. The description only restates serverUrl with an example URL, adding no semantics beyond the schema; baseline 3 applies.

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 poses a concrete question ("Is this MCP server safe to connect?") and enumerates what the report contains: permissions, risky tools, prompt-injection signs, and changes since the last check. That is a specific verb+resource an agent can act on. It stops short of a 5 because it does not name a sibling (e.g. get_trust_dossier_sample) to distinguish the free sample preview from the dedicated sample tool.

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 clear invocation guidance: pass a public serverUrl, or call with {} for a free sample preview, and notes there is no signup required. What is missing is explicit when-not guidance or a named alternative for the paid dossier path, which is only discoverable by reading the schema's paymentTxHash description.

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.