MCP examples

MCP server examples.

A curated list of MCP servers shipping in 2026, what they do, how they're configured, and the patterns worth lifting. All examples have public source — read the code before copying.

Completely free for 30 days. No credit card required.

01Teams

Reference servers from the MCP team

01

@modelcontextprotocol/server-filesystem — read/write local files. Good baseline for tool design (clear input schemas, scoped paths).

02

@modelcontextprotocol/server-fetch — fetch a URL and return its content. Cleanest example of a stateless tool with structured returns.

03

@modelcontextprotocol/server-memory — knowledge-graph memory the agent can read + write. Demonstrates resource exposure alongside tools.

04

@modelcontextprotocol/server-git — repo introspection (status, log, diff, blame). Shows how to handle filesystem-anchored state inside a tool.

05

@modelcontextprotocol/server-everything — every primitive the SDK exposes (tools, resources, prompts, sampling) in one place. The canonical end-to-end reference.

06

All open source at github.com/modelcontextprotocol/servers — read these first if you're learning the SDK. Older server-github / -postgres / -brave-search were archived in 2025; vendor-maintained replacements exist (e.g. github.com/github/github-mcp-server, github.com/stripe/agent-toolkit).

02Details

Browser automation

01

@playwright/mcp — Microsoft's official MCP server wrapping Playwright. Tools for navigate / screenshot / click / type. Stdio + HTTP modes.

02

sendblue-browser-mcp — wraps a stealth-patched Chromium daemon. Tools for navigate / screenshot / script eval / CDP attach. Useful when you need bot-resistant browsing.

03

Both ship as npm packages, install via npx -y <pkg>. Browser MCP servers are popular because agents need to test their own UI flows.

03Details

API + SaaS wrappers

01

Stripe (github.com/stripe/agent-toolkit), GitHub (github.com/github/github-mcp-server), Linear (community linear-mcp), plus Atlassian, Notion, Slack — official or strong community servers wrapping each provider's REST API.

02

Pattern: one tool per API operation, auth via env-supplied API key, structured returns matching the underlying response schema.

03

Most of these are hand-written today. Teams shipping more than 5-10 endpoints increasingly generate from OpenAPI to avoid the maintenance tax.

04Details

Patterns worth copying

01

Sanitise error messages — Playwright MCP and sendblue-browser-mcp both truncate Playwright's verbose error output to one line before returning. Avoids leaking internal IDs.

02

Allowlist URL schemes for any tool that takes a URL input — block file://, chrome://, etc. (the sendblue-browser-mcp navigate tool does this).

03

Cap input sizes — script.code capped at 200kB, cookies capped at 500 entries. Prevents agents from accidentally OOMing your server with a runaway loop.

04

Image returns as base64 with explicit mimeType — every screenshot-returning server uses this pattern.

05Details

Anti-patterns to avoid

01

Accepting API keys as a tool input parameter — agents will paste them into chat history. Always read auth from env.

02

Exposing every internal endpoint as a tool — pick the operations agents actually need; hide the rest.

03

Long tool descriptions — agents weigh tool selection by description length / clarity. Aim for one clear sentence.

04

Synchronous network calls that block the event loop — use async/await everywhere (Node) or asyncio (Python).

06Outputs

Generated from OpenAPI (preview)

01

MCP-server emission is in preview alongside Bloom's TypeScript and Python SDK pipeline — same OpenAPI input, same dashboard, with the patterns above baked in as they land.

02

Target output: one tool per operation, auth from env, error sanitisation, size caps, base64 image handling, sanitised allow-list for URL inputs.

03

Same workflow as Bloom's TypeScript/Python SDK generation (which ships today). Free for 30 days; no credit card.