Security

Codebase observatory with 56+ scanners for git health, architecture, and documentation.

Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.

Persistent, encrypted, deterministic memory for AI agents. Local-first, 173 canonical tools.

Access Obsidian vaults via Local REST API - read, search, and interact with notes

Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.

Guardian layer for AI agents: identity, secrets, audit via MCP.

Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.

MCP server for credential isolation — bots use passwords and API keys without seeing them

Secret management and multi-chain transaction signing for AI agents via MCP

A focused MCP server that issues request-bound, signed allow/block decisions before an x402 payment is signed.

Ybe Check – security and compliance orchestrator for AI-generated repositories.

Governed Keycloak + authentik identity ops: users, events, clients, MFA, RCA. 29 tools.

Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets.

Read-only MCP over a vault's typed knowledge graph: concept search, contradictions, article fetch.

Resolve a company domain to its GitHub organization with repo, language and activity signals.

Resolve company name, domain, or LinkedIn into one canonical identity with confidence scores.

Sick of stitched-together services? Anythink is the all-in-one backend, configured with AI.

Deploy a multi-user web app from your agent: hosting, auth, database, and permissions.

Universal AI API Orchestrator — 1,554 tools, 96 services. One install.

DNS and email security: check SPF, DKIM, DMARC, DNSSEC, DANE and build the records. 45 tools.