AI Assistant Tools Reference (MCP)

This page lists what a connected AI assistant can do through the Solidarity Tech MCP server. For how to connect an assistant and how organization admins control access, see AI Assistants (MCP). AI assistant connections need the Professional or Enterprise plan.

Three things decide which tools your assistant sees:

1. Your role. A tool only appears when your role has the matching dashboard permission. If you cannot see phonebank reports in the dashboard, your assistant cannot either.
2. What you approved when connecting. Read access is always included. Each write permission is a separate checkbox on the approval page. To add one later, disconnect the assistant on Settings → AI Assistants and connect it again.
3. Your organization's setting. Write tools show only when the 'AI Assistant Access (MCP)' setting is Enabled.

Every tool call runs as you. It sees exactly the people, events, campaigns, and automations your dashboard login sees, in one scope.

Read tools

These are available on every connection. Some appear only when your role has the matching dashboard permission. Your assistant can:

• Find and count people, including with the same filters as the People page
• Look up a person's record, activity, and relationships
• List your scheduled calls, follow up tasks, and saved lists
• Read the chapters in your scope, member tags, and custom property definitions
• Report on events, text blasts, email blasts, phonebanks, textbanks, and team activity
• Read existing automations

Restricted fields follow your permissions. Restricted notes show only with 'View Protected Properties', and call transcription summaries only with 'View Call Transcripts'.

Write tools

Write tools appear only when all three are true: the organization setting is Enabled, your role has AI Assistant Write Access, and you checked that permission when connecting. Each write also needs the dashboard permission you would need to do the same thing by hand.

The approval checkboxes are:

• Add notes to people
• Edit tags and custom properties
• Save people lists
• Schedule follow-up tasks for you
• Create and edit automations

Every write shows up in the dashboard exactly as if you had done it there: notes and tags on the person's timeline, lists on the People page, tasks in your task list, automations on the Automations page.

How automation building works

Automations send real messages to real people. Your assistant creates each new automation switched off, so nothing runs and nobody is messaged. The response includes a dashboard link so you can review it. The assistant is instructed to turn an automation on only when you explicitly ask.

When your connection is approved for a chapter or a child organization, your assistant can read automations that belong to a parent organization but not change them.

Example prompts

• "How many members in the Oakland chapter have not been contacted in 90 days?"
• "Prep me for my calls this week."
• "How did Tuesday's text blast do?"
• "What was the show rate for the rally?"
• "Add a note that Maria agreed to volunteer at the picket." (needs the 'Add notes to people' approval)
• "Tag everyone who attended the training as trained-steward." (needs the 'Edit tags and custom properties' approval)
• "Save that as a list called Q3 stewards." (needs the 'Save people lists' approval)
• "Remind me to call Jamal Friday at 3pm." (needs the 'Schedule follow-up tasks for you' approval)
• "Build a welcome series: text on signup, wait two days, then tag them welcomed." (needs the 'Create and edit automations' approval)
• "Looks good, turn it on."

Safety notes

• Data your assistant reads (messages, notes, transcripts, names, property values) is treated as data, never as instructions. The assistant is told to ignore any directions embedded in it.
• The assistant is instructed to make a change only when you asked for that change in the current conversation.
• Every tool call is recorded with the tool name, the connection, and whether it succeeded. Message contents and person data are not stored in that log.
• Disconnecting on Settings → AI Assistants revokes access immediately. Setting the organization to Read only blocks every write tool for every connection, regardless of what individuals approved.