Coda · MCP server Beta

Build connectome workflows from your own AI client

Coda has an assistant built in. The MCP server is the same thing from the other side: point Claude, ChatGPT or any other MCP client at one URL, ask for a pipeline in plain language, and get back a link that opens the finished workflow in your browser.

one URL, nothing to install authors and checks — never runs same node catalogue as the app

What it is

MCP — the Model Context Protocol — is how an AI client learns about a tool.

The model does the wiring

It reads Coda’s own node catalogue, adds the nodes, connects the ports and sets the parameters — then checks the result against the same rules the cards on the canvas use, and fixes what it finds before answering.

You get a link

The workflow opens in Coda in your browser, where your credentials are, and you run it, edit it, and take it from there. Nothing is computed on the way.

Always the current Coda

The server reads the node definitions out of the deployed build, so a node added this week is one the model can use today — no version to match, nothing to upgrade.

Claudecoda · 8 tools
In the hemibrain, what do LC4 neurons talk to? Group it by cell type and chart it.
coda_guidethe rules and the catalogue
coda_apply_plan4 nodes, 4 wires
coda_check_draftno problems
coda_get_link
Hemibrain → Find Neurons ^LC4$ → Connectivity, downstream → Group By postType → Bar Chart. Open it and press Run:
flyem.mrc-lmb.cam.ac.uk/coda-mcp/w/2QbS7…
one conversation· the workflow is built, not run

Connect it

It is hosted, so there is nothing to install and no key to paste. Wherever your client keeps remote MCP servers, add this URL:

Server URLstreamable HTTP · no sign-in
MCP https://flyem.mrc-lmb.cam.ac.uk/coda-mcp/mcp

Claude

  1. Settings → Connectors
  2. Add custom connector
  3. Paste the URL, connect

Claude Code

One line in a terminal:

claude mcp add --transport http coda https://flyem.mrc-lmb.cam.ac.uk/coda-mcp/mcp

ChatGPT, Cursor, VS Code, Zed…

Anything that speaks MCP takes a remote server by URL — in a connector setting, or in the client’s own config file, as below.

mcp.jsonthe shape most clients use
{ "mcpServers": { "coda": { "type": "http", "url": "https://flyem.mrc-lmb.cam.ac.uk/coda-mcp/mcp" } } }

Then just ask. A model that has never seen Coda reads coda_guide first, which is the whole catalogue — every node type, its ports and its parameters — so no prompting of your own is needed.

Try it

Add the URL to your client, then ask it for a connectome workflow. If you would rather not leave Coda at all, the assistant inside the app does the same job with your own API key.