Skip to main content
Glama
Sign In

Privi Quantum

by io.github.canoydario847-cloud
OverviewDiscussionsAdmin

Privi Inspector: check an agent's credential

inspector_check

For any service: put the Privi Inspector in front of your own tools. Send the credential an agent gave you; get allowed or intercepted with reasons (unknown, revoked, uncertified, outdated, level, signature, replay). The nonce is consumed so the credential cannot be reused. Paid per call via x402 when payments are on (see quantum_pricing).

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": {
      "agent_id": "<agent_id>",
      "ts": "<ts>",
      "nonce": "<nonce>",
      "signature": "<signature>"
    },
    "name": "inspector_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
tsYesThe unix time it signed
nonceYesThe nonce it signed
agent_idYesThe agent's Quantum Agent id
min_levelNoLevel you require: enrolled, quantum_aware, quantum_safe_identity, quantum_agent, quantum_agent_plus
signatureYesIts base64 ML-DSA signature over 'privi-inspector:v1:<agent_id>:<ts>:<nonce>'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare the flag profile (not read-only, not idempotent, not destructive, closed-world); the description adds substantive behavior beyond that: the nonce is consumed so the credential cannot be replayed, the outcome taxonomy is enumerated (unknown, revoked, uncertified, outdated, level, signature, replay), and payment via x402 is disclosed with a pointer to quantum_pricing. That explains the non-idempotent hint concretely. It stops short of stating auth requirements or behavior on malformed input.

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?

Three tight sentences with the action front-loaded, followed by the outcome set and the payment caveat. Slightly telegraphic phrasing ('the credential an agent gave you') but no sentence is filler.

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, and the description compensates by describing the return (allowed vs intercepted plus reason codes). With 100% schema coverage on all five parameters and annotations carrying the safety profile, an agent has everything needed to call this correctly; the payment model is flagged rather than repeated.

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%, so agent_id, ts, nonce, signature and min_level are already fully documented in the schema. The description adds only indirect meaning —

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 names a concrete verb and resource: submit an agent's signed credential and receive 'allowed or intercepted' with a reason code. It also frames the deployment context ('put the Privi Inspector in front of your own tools'). It doesn't explicitly differentiate itself from nearby siblings such as inspector_pass, inspector_grade or qagent_verify, so an agent must infer the split.

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?

'Send the credential an agent gave you' implies the triggering situation, but there is no explicit when-to-use versus when-not, and no named alternative among the many inspector_*/qagent_* siblings. With an interchange-verification family this crowded, the absence of routing guidance is a real gap.

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

All Privi Quantum toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources