MCP Studio

MCP is the open standard that lets AI assistants — like Cursor, Claude Desktop, and Windsurf — connect to external data sources and tools.

With MCP Studio, you turn documentation sites, GitHub repos, websites, PDFs, and MCP endpoints into a live MCP server that AI agents can query. You can also measure which context was used, how confident retrieval was, and which content needs improvement.

You add trusted sources → MCP Studio indexes the content → AI agents query that context through MCP → analytics show usage and impact.

After deployment, MCP Studio returns a config snippet like this:

{ "mcpServers": { "my-docs": { "url": "https://appatools.com/mcp-studio/api/mcp/my-docs" } } }

Use streamable HTTP (/api/mcp/{slug}) for new setups. Use/api/mcp/{slug}/sseonly for legacy compatibility.

Paste the snippet into your AI tool's MCP configuration:

- Cursor: Settings → MCP Servers → paste the JSON
- Claude Desktop: Settings → Developer → Edit Config → add tomcpServers
- Windsurf: MCP configuration file → add the server entry

Then ask questions that depend on your source content. Your AI agent can call the MCP tools during the conversation and retrieve grounded context.

- Total calls, success rates, and latency
- Which tools and sources are used most
- Recent call history with full query details
- Which MCP clients are connecting (Cursor, Claude, etc.)
- Which exact passages and source sections were used in calls (Action tier)
- Requests-to-working-answer trends and source quality grades (Predictive tier)

- Create an account— sign up and save your servers
- Adding sources— website URLs, GitHub repos, and private repos
- How it works— from source to answer, end to end
- Use cases— real-world examples and workflows

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Extentos is a multi-vendor development platform for adding smart-glasses capabilities to existing iOS and Android apps. The simplest analogy is Stripe for smart glasses

An MCP server tailored for React Native–first development using Gluestack UI

Create and read feature flags, review experiments, generate flag types, search docs, and interact with GrowthBook's feature flagging and experimentation platform.

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control.

Understand, develop, and debug authorization policies in Oso Cloud.

Up-to-date documentation for your coding agent. Covers 1000s of public repos and sites. Built by ref.tools

Points agents to the canonical Agentry install docs for errors, product analytics, and deploy attribution.

Gives coding agents deterministic, read-only documentation handoffs with edit boundaries, ownership, and required checks before repository changes.

Deterministic JSON checks with signed evidence and x402-paid execution