Docs & AI · Official remote MCP server

The AgentRead MCP server,
connected in one click.

Turn URLs, PDFs and DOCX into clean Markdown for agents, plus prompt-injection scanning. Connect the official AgentRead MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.

Connect AgentRead free How it works

Free to start · No credit card · No hosting needed

Use this server

Add AgentRead to your AI in one minute

Pick your client. Copy, paste, done — or let gate handle sign-ins and policies for you.

claude mcp add --transport http agentread-agent-read https://agent-read.toolschemaforge.workers.dev/mcp

Run in your terminal, then restart Claude Code.

AgentRead · https://agent-read.toolschemaforge.workers.dev/mcp

What you can do

What your AI can do with AgentRead

Real prompts you can type the moment it's connected — no setup, no docs to read.

“Use “read_url”: Read a public web page or document and return clean, LLM-ready markdown. Pricing: $0.001 (1 sat) per read, or $0.003 (3 sats) when scan is t.”

“Use “scan_text”: Scan text for prompt-injection risk and return a risk level, score, and signals. Pricing: $0.002 (2 sats) per scan. The free tier applies fi.”

Security check

How secure is the AgentRead MCP server?

Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how AgentRead holds up.

✓ Verified directory serverAgentRead · workers.dev

Official endpoint

Operated by AgentRead (workers.dev) at its documented MCP endpoint — not a third-party mirror or community re-host.

No sign-in needed

This server only exposes public data — no account and no credentials are involved when you connect.

Scanned before it goes live

gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.

Watched for drift

If AgentRead adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.

Run the free scanner on AgentRead's server →

How it works

Connected in three steps

Connect your gate

Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.

Pick AgentRead

Choose AgentRead in the gate directory. No sign-in needed.

Use it anywhere

AgentRead's tools are live in every AI client you've connected — with rules and logging built in.

Connect AgentRead free

Free to start · No credit card · No hosting needed

Straight from the server

The actual tools AgentRead exposes

Fetched live from the official endpoint and re-checked daily by gate — not marketing copy.

read_url — Read a public web page or document and return clean, LLM-ready markdown. Pricing: $0.001 (1 sat) per read, or $0.003 (3 sats) when scan is t

scan_text — Scan text for prompt-injection risk and return a risk level, score, and signals. Pricing: $0.002 (2 sats) per scan. The free tier applies fi

Author

Who runs the AgentRead MCP server?

workers.dev

Homepage More servers from workers.dev →

Own this server? Claim the listing →

Server facts

The AgentRead MCP server at a glance

Endpointhttps://agent-read.toolschemaforge.workers.dev/mcp

Operated byAgentRead (workers.dev)

CategoryDocs & AI

Sign-inNone — public data only

Available in gateYes — one-click connect

Works withClaude, ChatGPT, Cursor & any MCP client

FAQ

Questions, answered

Is there an official AgentRead MCP server?

Yes — AgentRead operates its own remote MCP server at agent-read.toolschemaforge.workers.dev. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.

How do I connect AgentRead to Claude or ChatGPT?

Add gate's gateway URL to your AI client once, then pick AgentRead in the directory. No account or sign-in is needed. From then on, AgentRead's tools are available in every client you've connected to gate.

Do I need to host anything?

No. AgentRead runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.

Is the AgentRead MCP server safe to connect?

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.