The Relm Report.

Schedule a Call
Model Context Protocol

The Relm MCP server

Give your AI agent 23 tools for commercial real estate: search any US property, run multi-agent Deep Search, build 10-year pro-formas, and read your portfolios — every finding traceable to a source.

Get an API key View pricing
https://api.relm.ai/mcp/

Connect in three steps

  1. Start a Relm subscription and create an API key in Settings → Developer.
  2. Add the server to your MCP client, authenticating with your key — pick your client for the exact config shape:
{
  "mcpServers": {
    "relm": {
      "url": "https://api.relm.ai/mcp/",
      "headers": { "Authorization": "Bearer relm_sk_..." }
    }
  }
}

Settings → MCP → Add server, or ~/.cursor/mcp.json

  1. Start prompting — your agent can now use the tools below.

23 tools for deal analysis

Read-only tools work with a read key; a full key adds the ones that trigger runs and edits.

Search & preview

Find properties and pull instant preview data.

  • search_properties

    Search your properties, portfolios, and uploaded documents by address, name, or keywords.

  • preview_property

    Fetch preview data (basic info, taxes, area stats) for a US address. Required before adding it to a portfolio.

  • get_preview_progress

    Check real-time progress of an in-flight preview.

Portfolios

Organize properties into portfolios.

  • list_portfolios

    List every portfolio with its id, name, and property count.

  • create_portfolio

    Create a new portfolio.

  • list_portfolio_properties

    List the properties in a portfolio (id, address, status).

  • add_to_portfolio

    Add a previewed address to a portfolio; returns the new property_id.

  • remove_from_portfolio

    Remove a property from a portfolio.

Deep research

Run and monitor multi-agent property research.

  • start_deep_search

    Start a full deep-research run — basics, units, comps, taxes, POIs, area stats, and a summary. Consumes one credit.

  • get_deep_search_status

    Per-section status plus a rollup (processing / complete / error / stopped) for a run.

  • get_run_steps

    A run's live activity trace; pass the cursor back to fetch only new steps.

Pro forma

Build, read, edit, and export the financial model.

  • start_proforma

    Start the 10-year financial pro-forma run. Requires an active subscription.

  • get_proforma

    Read the pro forma: Year-1 summary, 10-year projections, and line items.

  • edit_proforma_field

    Edit one pro-forma line item and save — either full 10-year values or a Year-1 value with a growth rate.

  • export_proforma

    Export the pro forma as xlsx, pdf, or json (temporary download URL).

Documents

Attach, index, and semantically search deal documents.

  • upload_document

    Attach a document to a property from a public URL or inline content. Pass index=true to kick off vector indexing immediately (returns an upload_id to poll).

  • index_document

    Start (or restart) vector indexing for an already-attached document so it becomes searchable/citable. Returns an upload_id to poll.

  • get_document_indexing_status

    Poll vector-indexing progress for an upload_id: pending, in_progress, complete, or failed.

  • search_documents

    Semantic (vector) search across your uploaded documents. Scope to one property, one portfolio, or search the whole org to find similar content anywhere.

Chats

Read your Relm AI chats and their transcripts.

  • list_chats

    List your chats — your org's shared 'edit' chats plus your private 'research' chats — newest first. Filter by portfolio, property, or type.

  • get_chat_messages

    Read a chat transcript, paginated by message index. Only chats you can see are readable.

Account

Inspect the key and its wallet.

  • get_credits

    The credit wallet: balance, plan, and whether new runs can start.

  • get_me

    Identify the API key: user, org, role, and scope.

Keys are scoped and revocable, calls are rate limited and isolated to your organization, and every research finding is traceable to its source. Your data is never used to train models.

Put a real estate analyst in your agent

Start a subscription, mint a key, and connect the Relm MCP server in minutes.

Get an API key