Kasbah MCP server

by Al-Adnane·io.github.Al-Adnane/kasbah-mcp·v3.0.1·2 stars

No reviews yet

Governance layer for agentic AI — signed, verifiable receipts for every agent action.

C69/100grade C

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

C69/100

full report

Adoption

New

2 stars44 downloads/wk

Reviews

Write one

Nobody has reviewed Kasbah yet.

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

Kasbah tools (16, 2 write)

write = sends, deletes, buys or posts

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

kasbah_advisorywrite action
Run a single advisory analyzer directly. Modules: detectgpt (AI-text),
kasbah_attest
Call this before any side-effecting action (file write, shell exec, HTTP
kasbah_check_compliance
Evaluate an agent action against pre-certified HIPAA, GDPR, SOC 2 Type II,
kasbah_compliance_report
Generate SOC 2 Type II / ISO 27001:2022 / NIST CSF 2.0 compliance evidence
kasbah_cost_guard
Runaway-loop and spend governor. Checks whether an agent is stuck in a tool
kasbah_export_audit
Export a tamper-evident, auditor-ready bundle of recent signed decisions.
kasbah_fti_query
Query the Federated Threat Intelligence registry. Checks whether a prompt
kasbah_govern_turn
Govern a full LLM turn through the Kasbah Governance Proxy: pass the message
kasbah_mcp_servers
List all MCP servers governed by Kasbah (ensemble, openclaw, ansari, quranfrontier).
kasbah_mcp_teams
Manage governance teams. Create, add members, assign MCPs, apply HIPAA/GDPR/SOC2/PCI-DSS policies.
kasbah_os
Access the kasbah-os engine (Python bridge). Defensive actions are live:
kasbah_redteamwrite action
Run the live red-team benchmark against the current governance pipeline.
kasbah_scan
Quick content scan through the Kasbah detector. Returns CLEAR / WARN /
kasbah_status
Show what Kasbah has done for you: decisions signed, actions blocked,
kasbah_trace_intent
Detect distributed, multi-step attacks invisible to single-step scanners:
kasbah_verify
Verify a Kasbah receipt cryptographically. Pass the receipt and its

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings

Code scan3 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 qualitystatic API keys via environment variables6/15
Maintenancelast push 121 days ago8/15
Maintainer identityregistry namespace matches repository owner6/10

Overall 69/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Kasbah compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 69/100; higher than 35% of 4,460 AI and agents servers
Tools: 16; the typical AI and agents server has 6
Tools that change things: 13%; typical: 0%. Fewer write tools means less an agent can break
GitHub stars: 2; more than 65% of 2,711 AI and agents servers
Downloads a week: 44; more than 36% of 1,538 AI and agents servers with a package

What its tools let an agent do: 14 read · 2 change

Install Kasbah in Claude Code, Cursor or VS Code

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

claude mcp add kasbah-mcp -- npx -y @yobekasbah/mcp-server

Add to Cursor

What the publisher says

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

Kasbah Core

Deterministic policy control for autonomous systems.

Kasbah Core is a minimal control plane that sits between AI agents and execution: it evaluates intent, enforces tool gates, and writes an append-only audit log.

This repo ships a runnable prototype for security engineers and CTOs.

Quick start (2 commands)

docker compose up --build

---

## 🔐 Minimal real API example (no demo, no UI)

This is a real Kasbah-Core runtime flow.
No simulation. No frontend. No policy-only logic.

STEP 1 — Ask Kasbah if an action is allowed

curl -s http://localhost:8002/api/rtp/decide \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer DEV_KEY" \
  -d '{
    "agent_id": "support-bot",
    "tool_name": "db.query",
    "signals": {
      "consistency": 0.95,
      "context": 0.90
    }
  }'

Example response:

{
  "decision": "ALLOW",
  "ticket": {
    "jti": "5a3bde1e887e000116e8943663b5088d",
    "expires_at": 1770307384
  }
}

STEP 2 — Execute the action using the issued ticket

curl -s http://localhost:8002/api/rtp/consume \
  -H "Content-Type: application/json" \
  -d '{
    "ticket": "5a3bde1e887e000116e8943663b5088d",
    "tool_name": "db.query",
    "usage": { "tokens": 120 }
  }'

Response:

{ "status": "ALLOWED" }

STEP 3 — Replay the same ticket (blocked by Kasbah)

curl -s http://localhost:8002/api/rtp/consume \
  -H "Content-Type: application/json" \
  -d '{
    "ticket": "5a3bde1e887e000116e8943663b5088d",
    "tool_name": "db.query"
  }'

Response:

{
  "status": "DENIED",

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

Kasbah: common questions

Is Kasbah MCP server safe?: With care: it is graded C, so read the findings first (69/100). Read the Kasbah safety report
How do I install Kasbah?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Kasbah need an API key?: Yes. The registry entry asks for KASBAH_API_KEY.
Is Kasbah maintained?: The last commit was 160 days ago (2026-05-28). The latest release is v3.0.1.
What can I use instead of Kasbah?: Servers from other publishers that do the same job: Emilia Protocol MCP server, three.ws Provenance MCP server and Attestix MCP server.
How does Kasbah compare with other AI and agents MCP servers?: safety score 69/100 (higher than 35% of 4,460 AI and agents servers); tools 16 (the typical AI and agents server has 6); tools that change things 13% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Kasbah

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

Emilia Protocol
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
not reviewed
Established
B
three.ws Provenance
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
More from nirholas →
not reviewed
Established
B
Attestix
AI agent identity, signed credentials, delegated authority and governance evidence.
not reviewed
Established
A
Ausca
Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
not reviewed
Established
A
agent-device
Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
not reviewed
Widely used
A

Run it through the gateway

Local package. It runs on your machine, not through the gateway.

Rating: —
Safety grade: C · 69/100
Stars: 2
Downloads/wk: 44
Price: Free
Licence: MIT
Transport: Local · npm
Version: 3.0.1
Category: AI and agents
Last release: 2026-05-28

Credentials it needs

KASBAH_API_KEYsecretKasbah API key — get a free one via POST https://kasbah-api.fly.dev/v1/auth/signup
KASBAH_APIKasbah gateway base URL (defaults to http://127.0.0.1:8788 for local dev)

Own this server?

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Claim listing

Badge for your README

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/al-adnane-kasbah-mcp.svg)](https://mcp.market/server/al-adnane-kasbah-mcp)

How the badge works