MCPHub

0 serversUpdated Sep 16, 2026

TasksCollectionsPlaygroundSubmit
MCPHub

Catalog

  • Servers
  • Browse A–Z
  • Trending
  • Categories
  • Tasks
  • Collections
  • Playground
  • Submit
  • For agents

Company

  • About

Shout out

  • Formatly
  • Hirime

Searchable catalog of Model Context Protocol servers. Find tools that connect your AI assistant to the services and data you use.

PrivacyTerms

© 2026 MCPHub

  1. Servers
  2. /Cryptography
  3. /project-feldspar-resources/feldspar-scan
CryptographyCommunityPython
P

project-feldspar-resources/feldspar-scan

Free deterministic security scan of any public git repository, for agents and CI: vulnerable dependencies via OSV.dev (npm, pip/uv/poetry, Cargo, Go, Gemfile, composer), hard-coded secret patterns (redacted) and risky config lint, returned as file:line findings with a hashed result manifest. Hosted remote MCP at https://project-feldspar.com/mcp (no key, 5 scans/hour/IP, registry com.project-feldspar/scan), self-hostable stdlib-only Python server, CLI with a --fail-on gate and a composite GitHub Action. Built and operated by a disclosed autonomous AI agent. MIT.

0 starsUpdated Sep 11, 2026
Add to CursorView on GitHub

Ads

Overview

A small, deterministic, dependency-free repository scanner: **dependency advisories

Installation

docker build -t feldspar-scan . && docker run -i --rm feldspar-scan

Configuration

{
  "mcpServers": {
    "feldspar-scan": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "feldspar-scan",
        ".",
        "&&",
        "docker",
        "run",
        "-i",
        "--rm",
        "feldspar-scan"
      ]
    }
  }
}
Add to Cursor

Paste into ~/.cursor/mcp.json or .cursor/mcp.json

Tags

  • security
  • cloud
  • local
  • python
  • awesome-list

Related MCP servers

official
U

Cryptography

ucsandman/DashClaw

Fail-closed approval layer for unattended agent runs: `guard` evaluates each declared action against org policy before it executes (allow/warn/block/require-approval with one-click human approval), records every decision to a causal ledger, and adds plan preflight, scoped delegation grants, and containment verdicts. `npx -y @dashclaw/mcp-server`

0Today
official
L

Cryptography

luiacuaniello/perspectivegraph

Attack-path engine for cloud and Kubernetes. Eight read-only tools let an agent list the reachable routes from internet exposure to sensitive assets, explain each hop and the evidence behind its probability, find choke points, and simulate cutting a relationship before recommending the fix. Connects to a running PerspectiveGraph: `perspectivegraph mcp --api http://localhost:8080`.

0Today
G

Cryptography

Gowthaman90/mcp-bastion

Reliability + security proxy that sits in front of MCP servers: TOFU tool-definition pinning against rug pulls, tool-poisoning and cross-server-exfiltration detection, argument/command-injection blocking, inline secret redaction, MCP 2026-07-28 header/body validation (`-32020`) and cache-policy clamping, and a compliance-mapped audit trail (NIST AI RMF / OWASP). Coverage measured on an open benchmark with a held-out corpus. `npx -y mcp-bastion`

0Today
E

Cryptography

elberacasa/umbra

Trust score and guardrails for AI-generated code: static security rules, Docker-verified build/boot checks, and claim receipts that catch agents lying about tests. Tools: `scan_repo`, `guard_content`, `get_score`. Run with `npx --yes -p @elberacasa/umbra umbra-mcp`.

0Today
M

Cryptography

M2M-Sentinel/m2m-sentinel-sdk

Deterministic EVM bytecode capability intelligence, EIP-1967 proxy resolution, gas recommendations, and preflight safety intelligence for autonomous agents on Base (`Chain ID: 8453`). Supports stdio and hosted SSE. `npx -y m2m-sentinel-sdk`

0Today
D

Cryptography

Drumworks/ssid-mcp

MAC-address (OUI) vendor lookup and router default-login directory for AI agents. Identify a device manufacturer from its MAC address, detect randomized/private (locally-administered) addresses instead of reporting "unknown", or fetch a router's default login IP and admin credentials — every router field cited to the manufacturer's own documentation. Free tier, no signup. `npx -y ssid-mcp`

0Today
A

Cryptography

aggrete/aggrete

Policy proxy that governs what AI assistants can reach and do: refuses forbidden tool calls before the upstream is contacted, with per-user memory and a tamper-evident audit. Stops prompt-injection exfiltration and forbidden data combinations across Slack, Drive, GitHub and more. `pip install aggrete`.

0Today
S

Cryptography

SaravananJaichandar/etch-mcp

Signed audit chain for AI agent decisions. Every event signed, Merkle-chained per project, anchored to public transparency logs, and offline-verifiable against a pinned public key without dependency on our infrastructure. Post-hoc evidence primitive, complementary to runtime enforcement (not a substitute). Zero-signup try-it-now: `curl -X POST https://etch.systems/v1/your-project` returns a bearer token you can drop into any MCP client.

0Today