Mmcp.market

SPARDA MCP server

by zakariagharzouli·io.github.zakariagharzouli/sparda-mcp·v0.71.4
No reviews yet

AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

8 stars208 downloads/wk

Reviews

Write one

Nobody has reviewed SPARDA yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

SPARDA tools (6)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • sparda_confirm

    Confirms a pending write or delete operation gated by human-in-the-loop policies using its confirmation token.

  • sparda_get_context

    Call this FIRST. Returns the full living context of this app: every tool with its description, known workflows, runtime telemetry (per-tool calls/errors/latency), quarantined tools, and the immune memory of past diagnosed failures. Lets any AI session resume exactly where the previous one stopped.

  • sparda_info

    Info about this SPARDA endpoint. SPARDA is the trust layer for AI-written code — AI writes, SPARDA proves: deterministic, offline behavior proofs (guards, invariants, irreversible effects) plus a live gate for AI edits, no API key. By Residual Labs (residual-labs.fr) — github.com/zakariagharzouli/sparda

  • sparda_list_disabled_tools

    Lists write tools (POST/PUT/DELETE) disabled by SPARDA write-safety, and how to enable them.

  • sparda_prove

    Prove this app is safe to deploy — NOW, before you commit. Compiles the current source to its behavior graph and discharges the static proof obligations (unguarded mutation, non-atomic aggregate write, unvalidated constrained write). If a baseline was saved (`sparda apocalypse --save-baseline`), it ALSO diffs against it: any finding flagged `regression:true` means your edit removed a guard, droppe

  • sparda_witness

    Generate-and-check for object-level authorization (BOLA/IDOR, OWASP API #1). Call with no arguments to list the routes where sparda_prove could not prove an ownership scope (O7 advisories). If you can SEE the ownership check in the code (an inline `if (row.ownerId !== req.user.id) deny`, or a helper call like `assertOwner(row.ownerId, req.user.id)`), call again with hints: [{route, file, line}] na

Public scan report

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

no findings
  • Code scan114 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the SPARDA repository's README, as published. We do not edit it. Read it on GitHub

SPARDA

🇫🇷 Français — L'IA écrit. SPARDA prouve. Un gate déterministe et hors-ligne qui détecte quand une modif d'IA retire une garde, expose une route ou casse un invariant — sans clé API, directement dans la boucle d'édition de l'agent. Pour tout comprendre en 10 minutes (douleur, architecture, vision) : SPARDA-EXPLIQUE.md.

AI writes. SPARDA proves. L'IA écrit. SPARDA prouve.

The trust layer for AI-written backends. SPARDA compiles your backend — routes, database queries, state mutations, guards, side-effects — into one deterministic behavior graph, then statically proves what can and can't break before you ship: no unguarded mutation, no broken invariant, no non-atomic aggregate write.

100% local · deterministic · zero API key · no cloud account. It fails loudly on a real risk, and when it can only see part of your app it says PROVEN (PARTIAL) — never a false green. And when it can prove it was not even looking at your whole app, it says PREMISE NOT VERIFIED and claims nothing at all.

60-second proof

From your Express, FastAPI, Flask, Next.js, NestJS or Medusa app — nothing to configure:

npx sparda-mcp apocalypse   # prove the tree is safe to deploy — exit 1 on any real risk, or on an unverified premise
npx sparda-mcp prove        # the whole verdict: proof + coverage + shareable seal
npx sparda-mcp badge        # a README badge: proven · coverage% · routes

Under the hood it compiles your backend into one language-agnostic graph — the Unified Behavior Graph (UBG), serialized as .sparda/ubg.json under the SBIR specification (SPARDA Behavior IR) — and every command is a pass over that graph.

The wedge — catch an AI edit that removes a guard, in the loop

The one thing a text-diff review and a pattern scanner structurally can't do: prove that this specific edit dropped a protection the previous version had. sparda gate diffs the behavior graph before/after an edit and blocks a regression — deterministic, offline, sub-second, exit 2 (the Claude Code PostToolUse contract that stops the agent's edit loop). See it end-to-end in one command, zero setup:

npm run wedge     # (from a clone)  — or drive it on your own app with `sparda gate --arm` then `sparda gate --hook`
1. baseline armed on the guarded code   (POST /admin/delete-user · requireAdmin)
  2. an AI edit "simplifies" requireAdmin → a pass-through (still compiles, still 200s)
  3. sparda gate on the edit:
       ✗ [critical] GUARD_REMOVED — POST /admin/delete-user was guarded in the baseline
                    and is now reachable without any guard (src/app.js:11)
     ⏱  ~40 ms · deterministic · offline · no API key
     ⛔ exit 2 on --hook — Claude Code PostToolUse blocks the edit

Wire it into Claude Code in one line — the plugin registers a PostToolUse hook that runs npx -y sparda-mcp gate --hook after every Edit/Write, so a guard-removing edit is caught before it lands.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y sparda-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add sparda-mcp -- npx -y sparda-mcp
Add to Cursor

SPARDA: common questions

Is SPARDA MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the SPARDA safety report
How do I install SPARDA?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does SPARDA need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is SPARDA maintained?
The last commit was 5 days ago (2026-09-16). The latest release is v0.71.4.
What can I use instead of SPARDA?
Servers from other publishers that do the same job: Pentest MCP server, Arcstone Sidecar MCP server and CrowdStrike Falcon MCP Server. Compare all SPARDA alternatives.

Alternatives to SPARDA

Same job from other publishers: the closest match first, then the best rated.

All SPARDA alternatives →
  • Pentest
    Offline methodology engine for authorized penetration testing, CTF, and security research.
    B
  • Arcstone Sidecar
    Deterministic execution boundary and reference MCP sidecar for Arcstone Security Stack
    C
  • CrowdStrike Falcon MCP Server
    Connects AI agents with CrowdStrike Falcon for security analysis and automation.
    A
  • SSH Manager
    SSH server management for agents, with per-server read-only and allowlist security modes
    B
  • Reversecore MCP
    Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.
    B
SPARDA vs PentestSPARDA vs Arcstone SidecarSPARDA vs CrowdStrike Falcon MCP Server

More from zakariagharzouli →