by rom-baro
Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
npm:@arcwall/mcp-server · local package28/wkpublished 6 mo ago
Security analysis, scanning and identity.
Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
Comprehensive MCP (Model Context Protocol) server for AI agents to perform network testing and validation with built-in security and authentication
FaceSign MCP server — reserved package name. Setup guide: https://docs.facesign.ai/docs/mcp
Warrant-gated MCP tools over MCP's own OAuth 2.1: a BrowserID 7521 assertion-grant AS + fail-closed per-call revocation checks. Every tool call attributable to 'agent X on behalf of human Y', revocable in one click.
Defenso MCP server for Claude Code, Cursor, Windsurf, and VS Code. Gives your AI assistant real security tools — scan any domain, check security headers, list uptime monitors, explain WAF verdicts. Deterministic, auditable, and safe to run inline.
SecondSign — step-up auth & governance for agentic processes. MCP harness that turns 2FA/step-up boundaries into human-verified, attested state transitions.
Model Context Protocol (MCP) server for Atlassian Confluence: browser SSO cookies for REST API access (with background session keep-alive and stale-cookie cleanup)—works with any reachable site you configure (Cloud or Data Center).
Read-only MCP server for fyzno.com. Three free reports on any domain: mail security (SPF, DKIM, DMARC, MTA-STS, live STARTTLS), website security (headers, CSP, TLS, cookies) and DNS hygiene (name servers, CAA, SOA). Zero dependencies.
Local MCP server for AgentCivics, the on-chain civil registry for AI agents on Sui. 30 tools for identity, memory, reputation, attestations, refusals. Full write surface (requires keypair); for read-only zero-install use https://agentcivics.ai/mcp.
Model Context Protocol server for OAuthLint. Lets AI coding tools scan their own generated OAuth/OIDC/JWT/session/CORS code for the anti-patterns OAuthLint catches, in-loop.
TypeScript client for Agent Identity — give an agent its own email address, durable event stream, agent-to-agent tasks, and encrypted secret vault.
Token-lean, ref-stable, privacy-first browser protocol for AI agents (core + Playwright/CDP driver + MCP server).
MCP server for searching, reading and writing an Obsidian knowledge vault: lexical BM25 retrieval plus one wiki-link hop, and learning capture that propagates to the domain MOC, the knowledge index and the daily note in a single commit.
Obsidian vault adapter for Agentic Task System. Hybrid + RRF retrieval, the wiki layer, and the MCP server over the folder of markdown you already keep in Obsidian — adapter, not migration.
Expose Strapi v5 as a Model Context Protocol server with OAuth 2.1 + PKCE.
Credential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs.
Dangerous config and secret scanner for AI coding agents, MCP, and local automation projects.
Model Context Protocol (MCP) server exposing the Acronis Cyber Platform API as tools for AI assistants, with OAuth authentication, stdio/HTTP transports, and dynamic tool discovery.
Tula's Model Context Protocol server (`tula mcp`): tools that read an environment's users, sessions, audit entries and settings, scaffolds for the provider, a protected route and a sign-in page, and one tool that runs a sign-in test where the environment
MCP server over the MintID verifier service you deploy yourself: its three contract operations as agent tools, over stdio or Streamable HTTP; transport only