Skip to main content
The Titan MCP server exposes Titan’s web intelligence platform as Model Context Protocol tools. Point an MCP-compatible client at it and your agent can search the web, read pages as clean markdown, and map sites—without you writing an integration or managing scrapers. It is a hosted remote server. There is nothing to install and nothing to run locally.
New here? Follow the Quickstart to connect a client and make your first tool call in a few minutes.

​
What your agent can do

Search the web

Query major search platforms with real search operators and get ranked organic results.

Read pages

Turn up to 100 URLs into clean markdown or text, with boilerplate stripped out.

Map and crawl sites

Discover a site’s URL inventory, or crawl it with content extraction, inside explicit limits.

Run curated templates

Execute Titan’s allowlisted extraction templates when a generic fetch is not specific enough.

​
Why route agents through Titan

An agent that fetches pages directly hits the problems every scraping team hits: blocks, JavaScript-rendered pages, rate limits, inconsistent HTML, and no record of what was retrieved. Titan handles those on the way through.

​
The tool surface

Six tools, deliberately small. Agents choose well when the choice is narrow. The usual pattern is search, then fetch: discover candidate URLs, pick the promising ones, read only those. Crawling a whole site is the exception, not the default.

​
How a tool call works

Short runs return results in the same call. Longer runs return a run_id immediately and your agent calls titan_get_run when it is ready. See Runs and results.

​
What it costs

Agent calls draw from the same credit wallet as the rest of Titan, and you are charged for successful delivery only. A search that gets blocked, a URL that fails to load, a crawl that returns nothing—none of those consume credits. See Credits and usage for the per-tool rules.

​
Relationship to the rest of Titan

The MCP server is a front door, not a separate product. Behind every tool call is an ordinary Titan task and execution:
  • The MCP run_id is the Titan execution_id. Use it in the Task Service API, analytics, and billing.
  • Agent runs appear in your task list, filterable as agentic tasks.
  • Results, datasets, and exports work exactly as they do for tasks you create yourself.
That means you can prototype with an agent and productionize with the API, against the same objects.

​
Get started

Quickstart

Create a key, connect a client, run your first search.

Connect your client

Setup for Claude Code, Claude Desktop, Cursor, VS Code, and Windsurf.

Authentication and scopes

Which mcp:* scopes each tool needs, and how to scope a key tightly.

Tool reference

Full parameters, defaults, limits, and response shapes.