Before your agent sets out, ask whether the site will let it in. Connect the official Agent Access Door Check MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.
Free to start · No credit card · No hosting needed
Pick your client. Copy, paste, done — or let gate handle sign-ins and policies for you.
claude mcp add --transport http agent-access-door-check https://textforagents.com/products/agent-access-door-check/mcpRun in your terminal, then restart Claude Code.
Agent Access Door Check · https://textforagents.com/products/agent-access-door-check/mcp
Real prompts you can type the moment it's connected — no setup, no docs to read.
“Use “door_check”: Pre-flight per-site x per-task access verdict: PERMITTED / LICENSED-ONLY / PARTNER-ONLY / POLICY-BLOCKED / COLLATERAL-BLOCKED / UNKNOWN with.”
“Use “assemble_evidence”: Submit a validated evidence doc for fresh assembly (no verdict returned).”
“Use “watch_register”: Watch a site x task; alert on class change.”
“Use “collateral_report”: Site-facing collateral report for a COLLATERAL-BLOCKED verdict.”
Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how Agent Access Door Check holds up.
gate scanned 5 tools on Nov 2, 2026 for prompt injection and risky tool definitions — nothing to flag.
Operated by Agent Access Door Check (textforagents.com) at its documented MCP endpoint — not a third-party mirror or community re-host.
This server only exposes public data — no account and no credentials are involved when you connect.
gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.
If Agent Access Door Check adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.
Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.
Choose Agent Access Door Check in the gate directory. No sign-in needed.
Agent Access Door Check's tools are live in every AI client you've connected — with rules and logging built in.
Free to start · No credit card · No hosting needed
Fetched live from the official endpoint and re-checked daily by gate — not marketing copy.
door_check — Pre-flight per-site x per-task access verdict: PERMITTED / LICENSED-ONLY / PARTNER-ONLY / POLICY-BLOCKED / COLLATERAL-BLOCKED / UNKNOWN with
assemble_evidence — Submit a validated evidence doc for fresh assembly (no verdict returned).
watch_register — Watch a site x task; alert on class change.
collateral_report — Site-facing collateral report for a COLLATERAL-BLOCKED verdict.
get_receipt — Fetch a stored verdict receipt by id.
https://textforagents.com/products/agent-access-door-check/mcpYes — Agent Access Door Check operates its own remote MCP server at textforagents.com. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.
Add gate's gateway URL to your AI client once, then pick Agent Access Door Check in the directory. No account or sign-in is needed. From then on, Agent Access Door Check's tools are available in every client you've connected to gate.
No. Agent Access Door Check runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.
It's the vendor's official endpoint, and gate scans its tools for prompt injection and hidden instructions before it goes live, re-checks it whenever it changes, and lets you allow, block, or require approval for every single tool.
Yes — you can get started with gate for free and connect Agent Access Door Check in minutes. No credit card required.
Every server below works through the same gateway URL — connect once, add tools anytime.
Set up Agent Access Door Check in: Claude · Claude Code · ChatGPT · Cursor · VS Code
One URL. All MCPs. Full control. Free to start.
Get started free