↓Skip to main content

MCP servers connect everything

Playbook
·3 mins
One MCP hub fans out to each system so Claude queries or updates through tools backed by real API calls.

Ticket IDs and Slack excerpts in the prompt worked until I pasted the wrong snippet and argued with Claude about navigation I’d already done twelve times. MCP flipped the pattern: register Slack, Confluence, mail—each server exposes list/search/read tools. The model calls the API; I stop narrating the org chart. One config block per system; capability grows without longer system prompts.

When I reach for this #

I keep fetching information outside the repo and pasting it back in. Or I want Claude to search structured systems (docs, mail, chat) with the same rigor it applies to files. Or I’m tired of context windows full of screenshots of UIs.

What I need before starting #

  • Claude Code (or your client) with MCP support enabled
  • API tokens or OAuth flows the server documentation requires — stored as env vars, not in chat
  • The install command or binary path for each server you plan to run

What I do #

MCP (Model Context Protocol) registers external tools — search, read, post, list — so the model calls them like built-in actions. Each server advertises a small API; Claude picks the tool when your question matches.

1. List the systems you actually touch weekly #

Start with two: one for async chat (Slack), one for searchable docs (Confluence). Add mail (Outlook) when triage or thread reconstruction is common. Add issue tracking (Jira) when status and comments live there. Stop when a server would run commands you never use — unused tools add noise to every turn.

2. Add each server to MCP config #

Most setups use a JSON or TOML block: command to launch the server, args, env for secrets. One entry per connector. Restart the client so it picks up the new registration.

3. Smoke-test with a narrow question #

“List my unread channels” beats “do my job.” Confirm auth, rate limits, and that returned payloads are usable. Fix token scopes before you rely on the server for real work.

4. Teach Claude when to prefer MCP over paste #

A line in CLAUDE.md or a skill helps: “For wiki questions, search Confluence first and cite what the tool returned.” The tools exist; routing still benefits from a nudge.

What goes wrong #

  • Over-privileged tokens — the server can read every channel with the same token you use for admin. Fix: use least-scope app tokens; rotate when people leave projects.
  • Tool sprawl — ten MCP servers and every answer starts with five irrelevant tool calls. Fix: disable servers you’re not actively using; merge overlapping connectors.
  • Latency stacks — each round trip to an external API adds seconds. Fix: batch questions; ask for summaries server-side when the tool supports it.
  • Broken servers masquerading as “empty results” — auth expired, wrong region, silent 403. Fix: watch stderr from the MCP process; add a health check command to your notes.

Notes #

Rollout — MCP turns chat into an ops console when the boundaries are clear. I adopt read-only search servers first, then add posting or ticket transitions after read paths feel routine.

Hygiene — public product names are fine; I treat internal instance URLs and space keys as sensitive. One config entry expands capability; maintenance is token renewal and server upgrades more than fresh prompt prose.