Glossary · Distribution

MCP server

A Model Context Protocol endpoint that exposes Twin as agent tools (run, compile_skill, run_skill) to MCP clients like Cursor, Claude Desktop, Claude Code, and Cline.

Start free All terms

What is mcp server?

An MCP server implements the Model Context Protocol so any compatible AI client can discover and call its tools over a standard interface. Twin’s MCP server exposes the execution layer as tools — `run` (execute a goal), `compile_skill`, and `run_skill` — so an agent in Cursor, Claude Desktop, Claude Code, or Cline can drive a real browser without bespoke integration code.

Why it matters

MCP is becoming the universal socket between agents and tools. Shipping a Twin MCP server means your IDE or desktop agent gets a browser — plus the semantic cache and replay economics — by adding one server, instead of wiring an SDK per client.

See it in context: read how Twin compiles and replays a run, follow the cost-cutting guide, or browse use cases and comparisons.

Related terms

Browser execution layer

The infrastructure that turns an agent’s goal into deterministic, replayable browser action — the layer between your LLM and a real browser.

Semantic dispatch cache

A vector cache that matches a new, re-phrased request to a skill you already compiled — so a repeated task skips the LLM.

Skill compilation

Turning a successful agent run into a reusable, replayable skill — a compact program of indexed actions you can call again without re-planning.

Credential vault

Encrypted per-tenant storage for the secrets a run needs — logins and tokens — injected at execution time and never exposed to the model or other tenants.

Back to the full glossary

Run your first skill

Give an LLM agent a real browser, compile the workflow once, and watch the marginal cost fall as the cache takes over.

Start free See pricing