Builders › MCP

The only crypto order-flow terminal.
With a native MCP server.

Connect an AI agent to drive the terminal and build indicators.

Connect your agent
Only on MMT
agent sessionmmt-mcp connected

> Set up a BTC footprint desk and write a CVD divergence script.

workspace_set_layout2x layout applied

widget_addchart · BTCUSD

chart_add_layerfootprint

script_createcvd-divergence.mmt

script_get_diagnosticspassed

script_editor_openopened

The footprint desk is live and the script compiled clean.

What you can ask it.

Drive the terminal

Apply a layout, add widgets, layers, and drawings, and read your current chart and workspace state.

> Give me a 2x2 desk with footprint and a heatmap.

Build indicators

Create, read, and edit scripts, even while MMT is closed, with the language reference and diagnostics in context.

> Write a script that flags CVD divergence.

Not a trading bot.
Bounded by design.

It does not place orders or send signals. Trading keys are a separate system, and publishing a script still needs builder approval. What an agent can do is bounded by the token scope you give it.

No ordersNo signalsTrading keys separatePublishing needs approval

Every tool, with its scope.

Sixteen tools across two families. Each one reads or writes, nothing else.

ToolDoesAccess
Drive the terminal
m5_get_statusRead workspace, session, and chart stateRead
workspace_set_layoutApply a layout presetWrite
widget_addAdd a widget to the workspaceWrite
chart_add_layerAdd an indicator or data layer to a chartWrite
chart_add_scriptAdd a script layer to a chartWrite
draw_tool_addAdd a drawing to a chartWrite
Build indicators
script_listList your scriptsRead
script_getRead a script and its latest revisionRead
script_createCreate a new scriptWrite
script_update_codeUpdate script codeWrite
script_update_metadataUpdate a script's name and metadataWrite
script_forkFork a source-visible scriptWrite
script_archiveArchive a scriptWrite
script_get_diagnosticsRead compile diagnosticsRead
script_editor_openOpen a script in the editorWrite
script_api_referenceRead the language referenceRead

Prompt to result.

Build an indicator headless

> Write a script that flags CVD divergence.

script_create

script_get_diagnostics

Saved and compiled, with MMT closed.

Set up a workspace by prompt

> Give me a 2x2 desk with footprint and a heatmap.

workspace_set_layout

widget_add

chart_add_layer

Layout applied and widgets added.

Fork and edit a public script

> Fork this indicator and change the length to 50.

script_fork

script_update_code

Forked, edited, and diagnostics clean.

Install for your client.

MMT generates copy-ready setup in the terminal. Agent setup also lives at/llms.txt.

Claude Code

generated command

Claude Desktop

JSON config

Cursor

JSON config

ChatGPT · Codex

generated config

Named tokens, scoped.

Create a named token, shown once and stored hashed. Publishing is never in scope, and you can revoke any token immediately.

Full controlRead and write across the terminal and script tools.
Full + metadata + archiveFull control, plus metadata edits and archiving.
Read-onlyRead terminal and script context, no writes.

Questions?
Answers.

Does it place orders?+

No. The MCP server drives the terminal and manages scripts. It has no order capability, and trading keys are a separate system.

Can it publish my scripts?+

No. An agent can create, edit, and archive scripts within scope, but publishing to the community catalog still requires builder approval.

Does it work when MMT is closed?+

Script creation and editing work headless, with MMT closed. Live control, opening the editor, and compile feedback need an open MMT session.

How do I revoke an agent?+

Revoke the token in settings and it stops working immediately. Tokens are shown once and stored hashed.

What can I let an agent do?+

You pick a scope preset when you create the token: full control, full control plus metadata and archive, or read-only.

Create a token and connect your agent.

Named, scoped, and revocable per agent.

Connect your agent