Skip to main content

Moveo One MCP

A Model Context Protocol server for Moveo One — behavioural intelligence for digital products.

Point Claude Desktop, Claude Code, Cursor, or any MCP client at your Moveo One workspace and it can integrate the SDK into your codebase, verify events are arriving, answer questions about your analytics, and build cohorts to run Quantum simulations against your app.

Install

uvx moveo-one-mcp login

That opens your browser to approve access. Credentials are cached in your OS keychain (falling back to a 0600 file at ~/.moveo/credentials.json).

Then register the server with your MCP client. Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "moveo-one": {
      "command": "uvx",
      "args": ["moveo-one-mcp"]
    }
  }
}

Claude Code:

claude mcp add moveo-one -- uvx moveo-one-mcp

You need a Moveo One account — sign up at app.moveo.one.

What it can do

Integrate — detect_stack scans your project and recommends an approach; add_sdk_snippet inserts the SDK for script-tag and npm projects; advise_gtm, advise_segment and advise_posthog return exact configuration for tools that live outside your codebase. get_integration_guide links the right docs page.

Verify — check_events_arriving confirms data is reaching Moveo One; watch_events and get_watch_status wait for the first event after you deploy.

Analyze — get_overview, list_dashboard_plots, get_plot, refresh_plot, and ask_analytics for natural-language questions over your data.

Simulate — create_cohort, discover_for_cohort, calibrate_cohort, then run_simulation to drive synthetic behavioural cohorts against your app. list_runs, get_simulation_status, list_sessions and get_session_screenshots follow a run; simulations take hours, so the assistant polls.

Models — list_prediction_models, get_prediction_model, get_prediction_model_metrics.

Two guided prompts, onboard and test_my_app, walk through the common flows.

Run whoami to check your connection and list_projects to see what you can reach. Most tools require a connected account; detect_stack and get_integration_guide work offline.

Configuration

Variable Default Meaning
MOVEO_ENV prod prod, dev, or local — selects backend and app URLs
MOVEO_API_BASE_URL derived from MOVEO_ENV Override the backend URL
MOVEO_REQUEST_TIMEOUT_SECONDS 75 Per-request HTTP timeout

Set these in the env block of your MCP client's server entry.

moveo-one-mcp logout clears stored credentials for the current environment.

Hosted server

A hosted version is available at https://hound.moveo.one for clients that support remote MCP servers over streamable HTTP with OAuth 2.1. It offers the same tools minus the ones that read and write your local filesystem.

Links

License

Proprietary — see LICENSE.

Metadata

Release files for moveo-one-mcp 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for moveo-one-mcp 0.1.0
File Size Uploaded
moveo_one_mcp-0.1.0.tar.gz 29.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for moveo-one-mcp 0.1.0
File Interpreter ABI Platform
moveo_one_mcp-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 70.4 kB

Release files / moveo_one_mcp-0.1.0.tar.gz

Download URL moveo_one_mcp-0.1.0.tar.gz
Size 29.6 kB
Tags Source
SHA-256 checksum
How to use checksums
3a8c4bf14a19024d44f4e5a432971201146634400bb5f8e2cb8c3528610d8a84
BLAKE2b-256 checksum
How to use checksums
0daea050363e4cc9f9185ccd402b02f04a4d2920a8edfcf016a94c97e0e7730b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 6, 2026.

Transparency log

Release files / moveo_one_mcp-0.1.0-py3-none-any.whl

Download URL moveo_one_mcp-0.1.0-py3-none-any.whl
Size 40.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9b655ad5b96aa266d8fa8548db383bdfd3c39057c1624470a493869ac7fb635d
BLAKE2b-256 checksum
How to use checksums
d392fc3ce9f92861004eb8ab87028836061a03593bc499326eebabe68ec09631
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 6, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page