nimbus-mcp

MCP server that lets AI agents (Claude Code, Cursor, Claude Desktop) build, validate, run, and analyze Nimbus BCI pipelines — upload their own EEG data, persist pipelines into studio projects, run multi-configuration experiment campaigns, watch live EEG sessions, and (explicitly confirmed) start live streaming — through your local Nimbus backend.

Install

pip install nimbus-mcp   # or: uvx nimbus-mcp

(Also installable from the repo: pip install -e nimbus-studio/mcp.)

Requirements

• A Nimbus backend running locally: the desktop app, or the dev server (cd nimbus-studio/backend-py && python -m nimbus_backend.server.app) with DEBUG=1.
• The backend started with MCP_LOCAL_KEY=<some-secret> (never set this on Fly — it is refused there).

Configure the backend

Desktop/dev env (e.g. backend-py/data/.env or the dev shell):

MCP_LOCAL_KEY=choose-a-long-random-string
MCP_LOCAL_USER_ID=user_your_clerk_user_id
DEBUG=1   # dev server only; the desktop app qualifies automatically

MCP_LOCAL_USER_ID sets the principal the MCP key authenticates as. Set it to your own Clerk user id (user_…) so everything the agent creates — projects, saved pipelines, executions — appears in your studio UI as yours. Pick one owner and stick with it: switching the id mid-life splits ownership of agent-created work across two principals, and neither identity then sees the whole history.

Watchdog default: streaming sessions started through MCP are auto-stopped after 15 minutes with no one watching (every stream_status / get_live_session poll resets the timer). Pass idle_timeout_sec=0 to start_stream to disable it for a session.

When enabling MCP_LOCAL_KEY on a machine connected to an untrusted network, also set HOST=127.0.0.1 on the backend — the default bind is 0.0.0.0, so the key would otherwise be accepted from the LAN.

Run the server

cd nimbus-studio/mcp
python -m venv .venv && source .venv/bin/activate
pip install -e ".[test]"
NIMBUS_MCP_KEY=choose-a-long-random-string python -m nimbus_mcp

Env vars: NIMBUS_API_URL (default http://127.0.0.1:8080), NIMBUS_MCP_KEY (must match MCP_LOCAL_KEY), NIMBUS_EXPORT_DIR (default ~/nimbus-exports).

Claude Code

claude mcp add nimbus -- <path-to-mcp-venv>/bin/python -m nimbus_mcp \
  --env NIMBUS_MCP_KEY=choose-a-long-random-string

Cursor / Claude Desktop (stdio)

{
  "mcpServers": {
    "nimbus": {
      "command": "<path-to-mcp-venv>/bin/python",
      "args": ["-m", "nimbus_mcp"],
      "env": { "NIMBUS_MCP_KEY": "choose-a-long-random-string" }
    }
  }
}

Tools (28)

Discovery: list_nodes, get_node_schema, list_templates, get_template, list_datasets Data: upload_data Build: validate_pipeline, validate_node_config Run: run_pipeline (non-blocking), get_execution, list_executions, get_results, cancel_execution Campaigns: run_experiment (non-blocking, 1-25 paced runs), get_experiment Artifacts: list_artifacts, download_artifact, export_python Live: list_devices, test_device, start_stream (needs confirm=true), stream_status, get_live_session, stop_stream Projects: create_project, list_projects, save_pipeline, load_pipeline

Uploading data

Bring your own recordings instead of (or alongside) the public datasets.

"I have a .edf recording at ~/recordings/session-01.edf — upload it and build a pipeline around it."

The agent calls upload_data(file_path=…), which registers the file with the backend and returns the stored path; that path goes into a custom_data node's config ({"filePath": "<path>", "format": "edf", …}) for validate_pipeline / run_pipeline / run_experiment.

Experiment campaigns

One run_experiment call = a paced sweep of 1-25 pipelines (at most 2 training runs in flight) with aggregated metrics, instead of the agent babysitting 25 individual run_pipeline polls.

"Compare CSP-LDA vs EEGNet on BNCI2014_001 across subjects 1-3."

The agent builds six train graphs, calls run_experiment(runs=[{name: "csp-lda-s1", train_graph: …}, …]), gets an experimentId back immediately, then polls get_experiment(experiment_id) until status is completed — per-run status and, at the end, aggregates like {"kappa": {"mean": 0.61, "std": 0.08, "best": {name, value}}} (mean/std/best over completed runs only).

Working with projects

Agent builds, human inspects. Pipelines the agent saves land in real studio projects, so you can open the canvas and see exactly what ran.

"Save this pipeline as a project called 'motor-imagery-baseline' — I'll review it in the studio."

create_project(name) makes the container, save_pipeline(project_id, train_graph) writes the graph (layout auto-generated, revision conflicts retried once) and load_pipeline(project_id) reads it back for editing or re-running. With MCP_LOCAL_USER_ID set to your user id, the project shows up in your studio project list.

Watching a live session

While a streaming session runs, the agent can watch its telemetry and tell you what it sees.

"Watch my focus session and tell me when signal quality drops."

The agent polls get_live_session(session_id) — latest prediction, the recent window, signal quality (meanChannelQuality, snrDb, artifactProbability) and running stats — and warns when quality degrades. Each poll also resets the idle watchdog, so a session under active watch is never auto-stopped; an abandoned one is shut down after 15 minutes.

Safety

start_stream refuses to run without confirm=true — it connects an EEG device and starts a live session on a human. The X-MCP-Key path is machine-local only (never accepted on Fly deployments). Sessions started via MCP are stopped automatically after 15 idle minutes (see the watchdog note above).