Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Beschreibung vom Entwickler (englisches Original)
Verifies Ed25519-signed attestation records and builds audit reports via MCP tools.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"mcpServers": {
"paceproof": {
"command": "npx",
"args": [
"-y",
"paceproof-cli",
"mcp"
]
}
}
}Führe das in deinem Terminal aus
claude mcp add paceproof -- npx -y paceproof-cli mcpIn .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"paceproof": {
"command": "npx",
"args": [
"-y",
"paceproof-cli",
"mcp"
]
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"paceproof": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"paceproof-cli",
"mcp"
]
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 7. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto RudrenduPaul bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 1 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Die Registry nennt keinen erforderlichen Schlüssel, manche Server bitten dich aber bei der ersten Nutzung, dich anzumelden.
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (0.1.1) kam vor 3 Monaten in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Node.js auf deinem Computer.
In derselben Kategorie: Spec Driven Development, Remote Desktop Commander, EmbeddedCI BenchPod
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
PaceProof verifies Ed25519-signed compute-attestation records from any provider and tells you exactly which ones are real.
A record with a missing, malformed, or tampered signature never gets folded into a "verified" total; it's counted and reported separately, every time, in both human-readable and --json output.
PaceProof does not sign or generate attestations. It is a neutral, read-only ingest/verify/report/dashboard layer over records that are already signed somewhere else. Point it at a directory, file, or URL of signed records and it tells you, verifiably, what compute was actually run, by whom, and whether every record's signature checks out.
paceproof-cli is published to both npm and PyPI:
npm install -g paceproof-cli
pip install paceproof-cli
Both commands install a paceproof binary. paceproof-cli is also available as an alias on both registries if you need to disambiguate from another tool on your PATH.
To build from source instead (useful if you're contributing, or want the exact repo state rather than a published release):
TypeScript (npm package, includes the MCP server):
git clone https://github.com/RudrenduPaul/PaceProof.git
cd PaceProof/packages/cli-ts npm install npm run build node dist/bin.js --help
Python (PyPI package, independent reimplementation):
git clone https://github.com/RudrenduPaul/PaceProof.git
cd PaceProof/packages/cli-py pip install -e . paceproof --help
Both the published npm install -g paceproof-cli and pip install paceproof-cli commands above were run fresh in a clean environment as part of writing this README, and the quickstart output below is real output from those installs, not fabricated.
paceproof init
paceproof report ./paceproof-example
paceproof init generates a fresh Ed25519 example keypair and 7 example attestation records: 3 validly signed, and 4 intentionally broken (a tampered payload, a wrong-key signature, a malformed signature, and a missing signature) so verify/report have real failure modes to demonstrate, not just a happy path.
Real output from an actual run against the published npm package:
$ paceproof report ./paceproof-example
PaceProof report -- source: ./paceproof-example generated at: 2026-08-04T02:54:30.898Z
== VERIFIED == records: 3 compute total: 144.50 gpu_hours
== UNVERIFIED (never counted in verified totals above) == records: 4 compute total: 1009 gpu_hours reasons:
== BY PROVIDER == acme-cloud: verified=132 gpu_hours (2 records); unverified_count=0 beta-compute: verified=12.50 gpu_hours (1 records); unverified_count=0 gamma-hpc: verified=(none); unverified_count=2 delta-cloud: verified=(none); unverified_count=2
== BY WORKLOAD TYPE == training: verified=128 gpu_hours (1 records); unverified_count=1 inference: verified=12.50 gpu_hours (1 records); unverified_count=1 idle: verified=4 gpu_hours (1 records); unverified_count=1 unknown: verified=(none); unverified_count=1
verify exits non-zero when any record fails (real exit code from an actual run: 1, with 4 unverified records present):
$ paceproof verify ./paceproof-example
Verified: 3 Unverified: 4 FAIL rec-004: signature does not match record contents FAIL rec-005: signature does not match record contents FAIL rec-006: signature must decode to 64 bytes, got 4 FAIL rec-007: schema validation failed: (root) must have required property 'signature' $ echo $? 1
Render a dashboard from the same data:
paceproof dashboard ./paceproof-example --out dashboard.html
Both the TypeScript and Python builds were run against paceproof-example for this README, and both produced the same verified/unverified counts and totals shown above.
ingest normalizes arbitrary input into the canonical schema through a documented Adapter interface (TypeScript interface, Python ABC). The shipped jsonl adapter reads newline-delimited JSON already in canonical form; a provider-specific adapter (e.g. for ComputeLedger's native export) implements the same interface without touching the aggregator, report renderer, or CLI wiring.report --json output for the same input; a CI job runs the TypeScript CLI's output against the Python CLI's output on a shared fixture in both directions and fails the build on any divergence.paceproof dashboard renders a single HTML file with inline CSS and no JavaScript: no CDN fonts, no external scripts, no remote requests of any kind. Currently ships one clean light theme; there's no dark-mode toggle yet.paceproof mcp starts a Model Context Protocol server exposing verify, ingest, and report as callable tools, so an orchestrating agent can call PaceProof programmatically instead of shelling out to a human-facing CLI. The tool handlers are thin wrappers around the same aggregator/report functions the CLI itself calls, with no separate reimplementation for the MCP path.Object.create(null) so an attacker-controlled provider or compute_unit field like "__proto__" can't pollute Object.prototype. The one network call PaceProof ever makes (ingest ) is bounded by a 30-second timeout and a 50 MiB response cap, enforced against the actual streamed byte count rather than trusting a Content-Length header. Every schema field carries an explicit maximum length so oversized input can't be used to exhaust memory before validation runs.Every table below is copied from the actual --help output of the published paceproof-cli npm package (v0.1.0).
paceproof init [path]Scaffold an example directory with a sample keypair and validly/invalidly signed example records.
| Argument | Description |
|---|---|
path | Directory to create (default: ./paceproof-example) |
paceproof verify Verify Ed25519 signatures on every record found at .
| Option | Description |
|---|---|
--json | Output structured JSON instead of a human-readable table |
--adapter | Adapter to use for reading input (default: jsonl) |
paceproof ingest Run a named adapter over the input and emit normalized canonical-schema records as JSONL.
| Option | Description |
|---|---|
--adapter | Adapter to use (default: jsonl) |
--out | Write JSONL output to a file instead of stdout |
paceproof report Ingest and verify records at , then aggregate into a summary report.
| Option | Description |
|---|---|
--json | Output structured JSON instead of a human-readable table |
--adapter | Adapter to use for reading input (default: jsonl) |
paceproof dashboard Render a single self-contained static HTML dashboard from a report.
| Option | Description |
|---|---|
--out | Output HTML file path (default: paceproof-dashboard.html) |
--adapter | Adapter to use for reading input (default: jsonl) |
paceproof mcpStart an MCP server exposing verify, ingest, and report as callable tools. TypeScript package only for now: running paceproof mcp from the Python package prints a message pointing to the npm package and exits non-zero.
Every command supports real non-zero exit codes on failure or verification failure, and --help on every subcommand.
The npm package also exports its internals directly (main/types in package.json point at real library code, not just the CLI entry point), for anyone building a custom adapter or embedding verification logic in another tool instead of shelling out to the CLI. This surface is TypeScript-only; the Python package exposes paceproof as a CLI only, with no documented import API.
import { getAdapter, verifyRecords, summarize } from 'paceproof-cli';
import type { Adapter } from 'paceproof-cli';
const records = await getAdapter('jsonl').read('./paceproof-example/records.jsonl'); const outcomes = verifyRecords(records); const report = summarize(outcomes);
| Export | Signature | What it does |
|---|---|---|
Adapter | interface Adapter { readonly name: string; read(input: string): Promise } | The extensibility point described above. Implement this to normalize a new provider's export format into canonical records. |
getAdapter(name) | (name: string) => Adapter | Looks up a registered adapter by name (jsonl ships built in); throws if the name isn't registered. |
verifyRecord(raw) | (raw: RawRecord) => VerificationOutcome | Schema-validates and signature-verifies a single record. |
verifyRecords(raws) | (raws: RawRecord[]) => VerificationOutcome[] | Runs verifyRecord over a batch. |
summarize(outcomes) | (outcomes: VerificationOutcome[]) => ReportSummary | Aggregates verification outcomes into the same verified/unverified-by-provider/by-workload-type structure paceproof report --json prints. |
verifyRecordSignature(record) | (record: AttestationRecord) => SignatureCheckResult | Checks only the Ed25519 signature (schema validation is separate), against the canonical JSON encoding described below. |
canonicalizeRecord(record) | (record: Record ) => Uint8Array | Produces the canonical byte encoding a signature is computed and checked over: lexicographically sorted keys, UTF-8, no insignificant whitespace. |
| buildCli() | () => Command | Returns the Commander.js Command instance the published CLI itself runs, if you want to embed or extend it rather than rei
Nur der Anfang wird gezeigt; den Rest findest du im Repo