ThinkWatch — Security skill for Claude Code
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.
How to install ThinkWatch
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ThinkWatchProject/ThinkWatch and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What ThinkWatch does
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.
Alternatives in Security
- Google Workspace Cloud Identity — Manage Cloud Identity groups and memberships 21.6k ★
- Azure Identity Go — Azure Identity for Go 1.8k ★
- MCP Security Checklist (SlowMist) — Comprehensive checklist: input validation, rate limiting, RBAC, credential management, container hardening 819 ★
README
ThinkWatch
**[English](README.md) | [中文](README.zh-CN.md)**
**A self-hosted AI API and MCP gateway for organizations.** Every model request and every MCP tool call passes through one gateway, where it is authenticated against the organization's identity provider, checked against limits and budgets, inspected by security guards, priced, and written to the audit log. It plays the role for AI access that a bastion host plays for server access.
**For individual developers:** [ThinkWatch Lite](https://github.com/ThinkWatchProject/ThinkWatch-Lite) is a free desktop app (MIT) that runs a local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux.
**Sponsors:** [Want to appear here?](mailto:fylorn@outlook.com?subject=ThinkWatch%20Lite%20Sponsorship)
┌──────────────────────────────────────┐
Claude Code ──────>│ │──> OpenAI
Cursor ───────────>│ Gateway :3000 │──> Anthropic
Custom Agent ─────>│ AI API + MCP │──> Google Gemini
CI/CD Pipeline ───>│
Related Skills
AegisGate
Open-source security gateway for LLM APIs — prompt injection detection, PII redaction, dangerous response sani
MCP Intercepter
Transparent proxy + enterprise gateway for MCP: audit logging, tool allow/deny policy, secrets/PII redaction,
Openclaw Gatewaystack Governance
Superseded by openclaw-acp-plugin. Policy layer for OpenClaw: identity, scope, rate limits, audit.
Aegis Proxy
Aegis: a guardrail proxy between coding agents (Claude Code, pi) and LLM providers. DLP redaction, an LLM judg
Sf Audit
Audit a Snowflake account — RBAC hygiene, warehouse topology, credit waste, recoverability, unmasked PII
Agent Observability Logging
Log everything that happens inside your agent system, from deterministic code: hook-written audit events, inva
Related Agents
Verina Pdpa Counsel
Senior legal counsel (Singapore data protection) for Verina. Use to ensure every data flow complies with the P
Identity Access Engineer
Identity and access domain advisor: OAuth2/OIDC, SSO, SCIM, WebAuthn, multi-tenant RBAC, session and token des
Appsec Auth Reviewer
Use proactively for deep-dive authentication and authorization security reviews: OAuth 2.0/OIDC implementation