Follow Up Boss MCP server for AI agents

Live

API KEY

REAL ESTATE CRM

CRM & Sales

Follow Up Boss gives your agent real estate CRM operations in each user's Follow Up Boss account: add and update leads, log calls and notes, book appointments, move deals through pipelines, and run action plans and automations.

  • Per-user credentials: each call uses the actual user's API key, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Follow Up Boss
agent · Acme Q3
Run
Which leads sent property inquiries today?
S
followupboss_events_list
115ms
Lead management agent
4 leads sent property inquiries today. 2 of them asked about the listing on Maple Street.
Sources: Follow Up Boss events, 4 inquiries
followupboss
4 events
18:29
Message Claude...

Tools your lead management agent reaches for on Follow Up Boss, scoped per user.

CALL ANY TOOL
85 tools for real estate CRM in Follow Up Boss: add and update people, log calls, notes, and tasks, book appointments, manage deals and pipelines, and run action plans and automations.
followupboss_action_plan_people_list
List action plan people
List action plans applied to a person, or people on an action plan, in Follow Up Boss. Returns assignments with their id, person, action plan and status (Running or Paused). Use it to find an assignment ID before pausing or resuming it with followupboss_action_plan_person_update.
Parameters
Name
Type
Required
Description
action_plan_id
integer
Optional
Return people on this action plan ID.
limit
integer
Optional
Maximum number of records to return, from 1 to 100. Follow Up Boss returns 10 when this is omitted.
offset
integer
Optional
Number of records to skip before returning results, used for paging (e.g. 25 to get the second page of 25). Results are newest first by default.
person_id
integer
Optional
Return action plans applied to this person ID.
followupboss_action_plan_person_apply
Apply action plan person
followupboss_action_plan_person_update
Update action plan person
followupboss_appointment_create
Create appointment
followupboss_appointment_get
Get appointment
followupboss_appointment_type_get
Get appointment type
followupboss_appointment_types_list
List appointment types
followupboss_automation_person_trigger
Trigger automation person
followupboss_automation_person_update
Update automation person
followupboss_automations_list
List automations
followupboss_call_get
Get call
followupboss_deal_create
Create deal
followupboss_deal_custom_field_get
Get deal custom field
followupboss_deal_custom_fields_list
List deal custom fields
followupboss_email_events_list
List email events
followupboss_email_template_update
Update email template
followupboss_event_get
Get event
followupboss_groups_round_robin_list
List groups round robin
followupboss_identity_get
Get identity
followupboss_note_create
Create note
followupboss_person_duplicate_check
Check person duplicate
followupboss_person_relationship_create
Create person relationship
followupboss_person_relationship_get
Get person relationship
followupboss_person_update
Update person
followupboss_pipelines_list
List pipelines
followupboss_smart_lists_list
List smart lists
followupboss_stage_get
Get stage
followupboss_team_inboxes_list
List team inboxes
followupboss_text_message_get
Get text message
followupboss_text_templates_list
List text templates

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Follow Up Boss tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["followupboss"], toolNames: [
    "followupboss_people_list",
    "followupboss_call_create",
    "followupboss_task_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Log my call with Sam Ortiz and create a task to send listings by Friday" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["followupboss"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Log my call with Sam Ortiz and create a task to send listings by Friday" }],
  tools,
});

// Execute the tool call with the user's vaulted Follow Up Boss API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["followupboss"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Log my call with Sam Ortiz and create a task to send listings by Friday" }],
  tools,
});

// Tool call runs with the user's vaulted Follow Up Boss API key
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["followupboss"] }, pageSize: 100,
});

const agent = new Agent({
  name: "lead_management_agent",
  model: "gemini-2.5-pro",
  instruction: "Follow Up Boss tools scoped to this user",
  tools,
});

await agent.run("Log my call with Sam Ortiz and create a task to send listings by Friday");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Follow Up Boss tool. Click to copy, paste into your agent, done.
Leads
Copy the prompt
Copied
Add Sam Ortiz as a new buyer lead from the open house.
Copy the prompt
Copied
List unclaimed leads offered to me.
Copy the prompt
Copied
Claim the lead for Sam Ortiz.
Follow-up
Copy the prompt
Copied
Log a call with Sam Ortiz and note that he wants 3 bedrooms.
Copy the prompt
Copied
Create a task to send Sam listings by Friday.
Copy the prompt
Copied
Start the New Buyer action plan for Sam Ortiz.
Deals and appointments
Copy the prompt
Copied
Book a showing with Sam Ortiz on Saturday at 11am.
Copy the prompt
Copied
Move the Maple Street deal to Under Contract.
Copy the prompt
Copied
List deals in the Buyers pipeline.
SEE HOW AUTH WORKS
Each user connects their own Follow Up Boss API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Follow Up Boss
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Follow Up Boss
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Follow Up Boss
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Follow Up Boss
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other CRM and sales connectors.
GTM and RevOps Teams
CRM AI agent
Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.
GTM and RevOps Teams
Outbound prospecting agent
Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.
Test other agents
See the same per-user auth pattern across other CRM and sales connectors.
GTM
CRM AI agent
Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.
SALES
Outbound prospecting agent
Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Follow Up Boss API key looks fine in a demo. In production every lead update and call log looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Follow Up Boss today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Follow Up Boss as the user or through a shared key?
As the user. Each user connects their own Follow Up Boss API key once, and Scalekit sends it with every call. Audit logs attribute every lead update, call log, and deal change to that user, not a shared service account.
Where is the Follow Up Boss API key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Follow Up Boss?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example read tools without followupboss_automation_person_trigger or followupboss_event_create, which run an automation or send new lead activity into the account. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Follow Up Boss access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent work with ponds and lead routing?
Yes, for reading and claiming. followupboss_ponds_list returns shared pools of unassigned leads, followupboss_groups_round_robin_list shows round robin groups, and followupboss_unclaimed_people_list lists leads offered to the connected user, who can claim one with followupboss_person_claim or pass with followupboss_person_unclaimed_ignore.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""followupboss"": {
""url"": ""https://mcp.scalekit.com/followupboss"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.followupboss]
url = ""https://mcp.scalekit.com/followupboss""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""followupboss"": {
""url"": ""https://mcp.scalekit.com/followupboss"",
""type"": ""http""
}
}
}