The real catalog of tools for AI agents

Advisory detectors for rumination, hyperfocus, and sycophancy. Never silently blocks.

Hosted NeuroDock — stateless communication and planning tools over OAuth-secured Streamable HTTP.

Decode subtext, tone, and ambiguity in messages; rewrite outgoing replies; brief meetings.

Externalises time-of-day, session boundaries, and break prompts for time-blind users.

A local typed-edge graph of people, projects, and decisions that externalises memory.

Decompose a vague goal into atomic 5-90 minute tasks and surface the next safe action.

Deterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.

Free spend guardrails for AI agents: approve/deny/ask_user, caps, dupes.

Cloudflare Workers MCP server: ai-guardrails

Deterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny.

An MCP server that provides Javelin Standalone Guardrails

Merge gates and safety checks for AI coding agents via MCP.

Action-level governance for AI agents -- control what they DO, not what they SAY

Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation

AI Agent Guardrails MCP server - security layer

Keyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt.

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails

Access Oi Contexts, Workflows, Skills, Guardrails, Connections, and reporting tools.

Read-only MCP for identity resolution and write guardrails.