Privi Quantum

Crypto inventory (CBOM) for a company

pqc_crypto_inventory

Point Privi at a company's domains and GitHub repositories and get one cryptographic bill of materials: every algorithm quantum computers will break, where it is, a prioritized migration plan with dates, a CycloneDX 1.6 CBOM and a public report page, signed with ML-DSA-87 and anchored on chain. Repos are scanned in memory and not kept. Paid per call via x402 when payments are on (see quantum_pricing); failed calls are not charged.

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": {
      "organization": "<organization>"
    },
    "name": "pqc_crypto_inventory"
  }
}

Input Schema

Name	Required	Description	Default
`files`	No	Extra code or config files: [{name, content}] (up to 50 files, 1 MB)
`repos`	No	Public GitHub repositories to scan, e.g. ['https://github.com/acme/api', 'acme/web'] (up to 5)
`assets`	No	Known cryptographic assets (same shape as pqc_readiness_package)
`domains`	No	Public hostnames to test live for TLS 1.3 and hybrid post-quantum key exchange (up to 20)
`profile`	No	company (NIST IR 8547 dates) \| agency \| contractor \| nss_vendor	company
`organization`	Yes	Company or agency name
`long_lived_data`	No	Do these systems protect data that must stay secret past 2030? Raises priority (harvest now, decrypt later)

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A3.9/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses data-handling behavior (repos scanned in memory and not kept), billing behavior (paid per call via x402, failed calls not charged), and the artifact signing/anchoring chain (ML-DSA-87, on-chain). These are exactly the facts an agent needs before triggering a non-idempotent, externally-visible call.

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?

Front-loaded with the outcome, then behavior and billing, in three efficient sentences with no filler. The first sentence is overstuffed with a four-item output list, but each clause carries real information.

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?

No output schema exists, and the description compensates by describing the deliverables, verification method, and data-retention policy. For a 7-parameter, non-idempotent, open-world call the picture is nearly complete, though failure modes and turnaround/latency 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 description coverage is 100%, so the baseline applies. The description only gestures at the two headline inputs (domains, GitHub repositories) and adds no format, limit, or interaction detail beyond what the schema already documents; the files, assets, profile, and long_lived_data parameters are untouched.

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: point the service at domains/repos and receive one cryptographic bill of materials, with the concrete artifacts enumerated (CBOM, prioritized migration plan, report page). It is clearly the company-wide aggregate, but it never names the narrower siblings (pqc_scan_code, pqc_endpoint_check, pqc_readiness_package) that an agent might otherwise pick.

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?

Usage is implied by the scope (whole company, multiple input sources) and there is one explicit pointer for a related concern (see quantum_pricing when payments are on). There is no statement of when to prefer this over pqc_scan_code or pqc_readiness_package, and no prerequisites or exclusions.

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

All Privi Quantum tools Inspect

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.