# quantakrypto pqc-tools (npm · @quantakrypto/mcp)

Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.

- Trust score: 79/100 (medium)
- Change this week: −16
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.quantakrypto.com`: 79/100, [markdown](https://verifymcp.io/servers/quantakrypto-pqc-tools/mcp.md), [page](https://verifymcp.io/servers/quantakrypto-pqc-tools/mcp)
- npm · `@quantakrypto/mcp`: 79/100 (this document), [markdown](https://verifymcp.io/servers/quantakrypto-pqc-tools/quantakrypto-mcp.md), [page](https://verifymcp.io/servers/quantakrypto-pqc-tools/quantakrypto-mcp)

## Channel facts

- Registry: `npm`
- Package: `@quantakrypto/mcp`
- Version: `0.5.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 2 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to quantakrypto/pqc-tools).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1838 tokens (~102/item across 18 items; 16 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add quantakrypto-pqc-tools -- npx -y @quantakrypto/mcp
```

### Codex

```bash
codex mcp add quantakrypto-pqc-tools -- npx -y @quantakrypto/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "quantakrypto-pqc-tools": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@quantakrypto/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add quantakrypto-pqc-tools --command npx --arg -y --arg @quantakrypto/mcp
```

### Hermes

```yaml
mcp_servers:
  quantakrypto-pqc-tools:
    command: "npx"
    args: ["-y", "@quantakrypto/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "quantakrypto-pqc-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@quantakrypto/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-01 (score 64, −13)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 77, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 95, +36)

- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: good

### 2026-07-26 (score 59)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (16)

### `apply_triage` (~94 tokens)

Deterministically attach your triage verdicts to their findings and re-sort by exposure (highest first). Never suppresses. Pass the same 'findings' array you triaged plus a 'verdicts' array of { fingerprint, exposureScore, priority, rationale }.

Input parameters:

- `findings` (array, required): The findings that were triaged.
- `verdicts` (array, required): One verdict per finding, keyed by fingerprint.

### `apply_verified_patch` (~168 tokens)

Deterministically VERIFY a proposed fix before writing it — runs the same patch-policy + verify_fix + blast-radius gates as `qremediate` (offline, no key, no network). Give the finding, the file's current content, and your proposed FULL corrected content; returns approved:true only if the patch is in-policy, clears the finding, adds no new finding, introduces no network/exec sink, and is bounded in size. This does NOT write the file — you write it, only when approved, and never auto-merge.

Input parameters:

- `finding` (object, required): The scan finding being fixed (needs a string ruleId and location.file).
- `newContent` (string, required): Your proposed full corrected file content.
- `originalContent` (string, required): The file's current full content.

### `check_dependency` (~82 tokens)

Check whether a package is in quantakrypto's known quantum-vulnerable dependency database (the classical crypto it exposes). Provide 'name' and optional 'ecosystem' (default npm).

Input parameters:

- `ecosystem` (string): Package ecosystem. Default: npm.
- `name` (string, required): Package name to look up (e.g. 'node-forge', 'jsonwebtoken').

### `explain_finding` (~135 tokens)

Explain a quantakrypto finding and its post-quantum remediation. Provide a ruleId (e.g. 'forge-rsa-keygen', 'elliptic-ec', 'node-rsa', 'pem-ec-private-key') and/or an algorithm (e.g. 'RSA', 'ECDSA'). The ruleId is resolved against the core detector set, so library and config rules explain correctly.

Input parameters:

- `algorithm` (string): The classical algorithm family involved (e.g. RSA, ECDH, ECDSA).
- `ruleId` (string): The finding's rule id, matching a detector id prefix.

### `generate_cbom` (~78 tokens)

Scan a path and emit a CycloneDX 1.6 Cryptographic Bill of Materials (CBOM) of the classical cryptographic assets found, for compliance / supply-chain tooling. Reads the filesystem, so it is gated like scan_path over HTTP.

Input parameters:

- `path` (string, required): Absolute or relative path to a file or directory to inventory.

### `get_fix_examples` (~90 tokens)

Return before/after code examples for migrating a classical algorithm to a post-quantum / hybrid replacement. Provide an 'algorithm' (RSA, ECDH, ECDSA, …) or a 'ruleId' from a finding.

Input parameters:

- `algorithm` (string): Classical algorithm family to migrate away from.
- `ruleId` (string): A finding's ruleId (resolved to its algorithm).

### `inventory_crypto` (~59 tokens)

Produce a post-quantum readiness inventory for a path: a 0-100 readiness score plus counts of cryptographic findings by algorithm, category, and severity.

Input parameters:

- `path` (string, required): Absolute or relative path to a file or directory to inventory.

### `list_rules` (~25 tokens)

List the quantakrypto detector catalog: every detector id and what it looks for.

### `plan_migration` (~86 tokens)

Scan a path and return a deterministic, prioritized post-quantum migration plan: findings grouped by algorithm, ordered harvest-now-decrypt-later first, each with its PQC target and the readiness-score impact. Reads the filesystem, so it is gated like scan_path over HTTP.

Input parameters:

- `path` (string, required): Absolute or relative path to a file or directory to plan a migration for.

### `probe_endpoint` (~239 tokens)

Actively probe ONE live TLS/SSH endpoint YOU OWN for post-quantum readiness (PQC-hybrid key exchange X25519MLKEM768, classical certificate posture). REQUIRES an ownership attestation: set i_own_this=true to confirm you are authorized to test the target. Refuses CIDR ranges / wildcards / lists — one host at a time. Performs only a benign, unauthenticated handshake and never modifies the endpoint. NOTE: this is the ONLY quantakrypto MCP tool that opens a network connection; the server is otherwise offline. Over HTTP it is disabled unless the operator sets QUANTAKRYPTO_MCP_ALLOW_NETWORK=1.

Input parameters:

- `i_own_this` (boolean, required): Attestation that you are authorized to probe this endpoint. Must be true; the probe is refused otherwise.
- `mode` (string): Probe mode (default: auto — SSH on :22, TLS otherwise).
- `target` (string, required): A single host or host:port you own (no ranges/CIDRs/wildcards).
- `timeout_ms` (number): Per-connection timeout in ms (default 8000).

### `remediate_findings` (~112 tokens)

Produce a deterministic remediation REQUEST bundle (rubric + fix schema + per-finding metadata + fingerprints) for YOU (the host agent) to fix. This tool calls no model and needs no key. For each finding, propose the corrected FULL file content, then VERIFY with verify_fix and keep only fixes that clear the finding. Never touch files with secrets; never auto-merge. Pass 'findings' from scan_path --format json.

Input parameters:

- `findings` (array, required): Findings from a scan's JSON output.

### `scan_path` (~83 tokens)

Scan a file or directory for classical (quantum-vulnerable) asymmetric cryptography using quantakrypto. Returns a readiness summary and findings.

Input parameters:

- `format` (string): Output format: 'summary' (default) for readable text, 'json' for the raw ScanResult.
- `path` (string, required): Absolute or relative path to a file or directory to scan.

### `score_delta` (~79 tokens)

Compute the readiness-score and HNDL change between two finding sets (e.g. before and after a migration). Pass 'before' and 'after' as arrays of findings from scan_path --format json.

Input parameters:

- `after` (array, required): Findings after the change.
- `before` (array, required): Findings before the change (from a scan's JSON findings).

### `suggest_hybrid` (~172 tokens)

Recommend a post-quantum / hybrid migration. Provide an 'algorithm' (e.g. RSA, ECDH, ECDSA) or free-text 'context' describing the usage. Set 'tier' to 'category-5' for CNSA 2.0 / national-security systems.

Input parameters:

- `algorithm` (string): Classical algorithm family to migrate away from.
- `context` (string): Free-text description of the cryptographic usage (used when no algorithm is given).
- `tier` (string): Security tier: 'category-3' (default, commercial — ML-KEM-768 / ML-DSA-65) or 'category-5' (CNSA 2.0 / NSS, long-lived secrets — ML-KEM-1024 / ML-DSA-87).

### `triage_findings` (~100 tokens)

Produce a deterministic triage REQUEST bundle (rubric + verdict schema + per-finding metadata) for YOU (the host agent) to reason over. This tool does NOT call any model and needs no API key. Assess each finding's real-world exposure, then call apply_triage with your verdicts. Pass 'findings' as an array from scan_path --format json.

Input parameters:

- `findings` (array, required): Findings from a scan's JSON output.

### `verify_fix` (~123 tokens)

Run the quantakrypto detectors over a code snippet (NOT the filesystem) and report any classical crypto that remains. Use this to confirm an edit actually removed the quantum-vulnerable usage. Provide 'code' plus a 'language' or 'filename'.

Input parameters:

- `code` (string, required): The source code to check.
- `filename` (string): Optional filename; its extension selects the detectors (overrides 'language').
- `language` (string): Language of the code (js, ts, python, go, java, csharp, rust, ruby, c, …).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/quantakrypto-pqc-tools/quantakrypto-mcp#diagnostics

## Score history

- 2026-08-03: 79
- 2026-08-02: 79
- 2026-08-01: 64
- 2026-07-31: 77
- 2026-07-29: 95
- 2026-07-28: 95
- 2026-07-27: 95
- 2026-07-26: 59

## Links

- npm package: https://www.npmjs.com/package/@quantakrypto/mcp
- Socket report: https://socket.dev/npm/package/@quantakrypto/mcp
- Repository: https://github.com/quantakrypto/pqc-tools
- Changelog RSS feed: https://verifymcp.io/servers/quantakrypto-pqc-tools/quantakrypto-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/quantakrypto-pqc-tools/quantakrypto-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/quantakrypto-pqc-tools/quantakrypto-mcp