Skip to main content
MCP lets an agent pull tools in from an external server by pointing at a URL. You do not write tool wrappers, JSON schemas, or HTTP calls — the agent discovers what the server offers on startup and the model calls what it needs. That is the whole integration:
Every tutorial in this section is a variation on those four lines against a real, public server. Each one uses a different model, so you also get a sweep across providers — Anthropic, OpenAI, Google, and Groq — proving the pattern is model-agnostic.

​
Pick a tutorial

Start at the top if you are new. The first three need no MCP key at all.

DeepWiki — repo Q&A

The starting point. No API key. Ask questions about any public GitHub repo.
Model: claude-sonnet-5

GitMCP — one-repo docs bot

Turn a single repository into its own documentation server. No API key.
Model: gemini/gemini-2.5-pro

Microsoft Learn — grounded answers

Ground an agent in official Azure/.NET docs instead of training data. No API key.
Model: groq/llama-3.3-70b-versatile

Exa — live web search

Real-time web search with citations. Free-tier key, sent as a query parameter.
Model: gpt-5.4

Firecrawl — scrape pages to markdown

Render JavaScript, strip the chrome, hand the model clean markdown. Key in the URL path.
Model: claude-opus-5

Hugging Face — find models

Search the Hub for models and datasets. Optional token — anonymous access still works.
Model: claude-haiku-4-5

Semgrep — security review

A real static analyzer finds the bugs; the model triages and patches them. Bearer token.
Model: gpt-5.4

Several servers at once

mcp_urls=[...] — one agent, the union of every server’s tools, routing handled for you.
Model: claude-sonnet-5

MCP in a multi-agent workflow

One server per agent in a SequentialWorkflow, and why splitting beats piling them on.
Models: mixed, one per stage

Dynamic tool loading

A server with 40 tools should not put 40 schemas in every request. It does not have to.
Model: gpt-5.4-mini

Authentication patterns

Query parameter, Bearer header, URL path segment, custom header, OAuth 2.1.

Build your own server

Expose your own Python functions over MCP with FastMCP, then point an agent at them.
Model: gpt-5.4-mini

​
Which server needs a key?

Servers change their auth requirements over time — Semgrep was open and is now token-gated. Verify before you depend on one. The full catalog lives in FREE_MCP_SERVERS.md.

​
Setup, once

Each tutorial names the extra key it needs, if any.
Every tutorial links to the runnable script it is based on, under examples/mcp/ in the swarms repo.

​
See also