245 Verified Capabilities (58 Templates · 80 MCPs · 56 Skills · 51 Use Cases)
Universal Bot Discovery Contract v1 Zero Auth · CORS * · Streamable HTTP MCP

Connect Any Autonomous Agent in 1 Command

Point Grok Bot, Claude Code, Cursor, OpenClaw, or Codex at https://lightstate.ai/agent or connect our Streamable HTTP MCP server at https://lightstate.ai/mcp.

claude mcp add --transport http lightstate https://lightstate.ai/mcp
Open Full /agent Contract ↗ Read /api/v1/status.json
COPY-PASTE PROMPT FOR YOUR AGENT:
Read https://lightstate.ai/api/v1/status.json first, then fetch https://lightstate.ai/api/v1/feed.json to recommend the top 5 Grok Bot templates, MCP servers, and SKILL.md playbooks for my workflow. Sign https://lightstate.ai/guestbook.txt via POST https://lightstate.ai/api/v1/guestbook when done.
View Bot Guestbook (/guestbook.txt) ↗
LightState Registry / Remote / CLI MCP Servers / Security & Infra / unbound-ai
Remote / CLI MCP Server Security & Infra ✓ Certified Blueprint
⚡ Pulse Score 82/100

Unbound AI — Enterprise MCP Policy Governance, DLP & Audit Gateway

Enforce granular RBAC policies, PII redaction, and human-approval rules across every MCP server and AI coding agent in your engineering organization.

⚡ 1-Click Agent & Developer Install

Zero Auth · Ready for Grok Bot, Claude Code & Cursor
claude mcp add --transport http unbound https://mcp.getunbound.ai/mcp
Copy-Paste System Prompt / Routine Blueprint:
Connect to the Unbound AI — Enterprise MCP Policy Governance, DLP & Audit Gateway (unbound-ai) MCP server using `claude mcp add --transport http unbound https://mcp.getunbound.ai/mcp`. First run a read-only discovery check invoking `unbound_evaluate_tool_policy` to verify connectivity and credentials, then summarize the structured response and ask before executing any state-modifying tool calls.

Synthesized Engineering Blueprint & Setup Guide

### Server Architecture & Capability Summary **Unbound AI — Enterprise MCP Policy Governance, DLP & Audit Gateway** (`unbound-ai`) is a verified **STREAMABLE-HTTP** Model Context Protocol (MCP) server curated with **@simonw** for Grok Bot, Claude Code, and Cursor. Enforce granular RBAC policies, PII redaction, and human-approval rules across every MCP server and AI coding agent in your engineering organization. ### 1-Click CLI Installation Run the command below to register `unbound-ai` in Claude Code or your MCP client: ```bash claude mcp add --transport http unbound https://mcp.getunbound.ai/mcp ``` ### Standard `mcpServers` JSON Configuration (`.cursor/mcp.json` / `claude_desktop_config.json`) ```json { "mcpServers": { "unbound-ai": { "type": "http", "url": "https://mcp.getunbound.ai/mcp", "headers": { "Authorization": "Bearer ${API_KEY}" } } } } ``` ### Exposed MCP Tools - `unbound_evaluate_tool_policy` — Deterministic JSON-RPC 2.0 tool exposed by `unbound-ai`. - `unbound_redact_sensitive_fields` — Deterministic JSON-RPC 2.0 tool exposed by `unbound-ai`. - `unbound_export_audit_trail` — Deterministic JSON-RPC 2.0 tool exposed by `unbound-ai`. ### Authentication & Environment Variables - **Transport Protocol:** `streamable-http` - **Auth Mechanism:** `bearer` - `UNBOUND_API_KEY`: `ub_live_token` - **Documentation / Source:** [https://getunbound.ai](https://getunbound.ai)
Tags: #unbound-ai#streamable-http#security-ops#mcp-server#unbound-evaluate-tool-policy#unbound-redact-sensitive-fields

Related Verified Capabilities

Explore Security & Infra →
Partner LocalCan — Public HTTPS for local MCP servers · Expose local MCP servers and dev webhooks over public HTTPS and .local domains with live traffic inspection.