ServiceM8 MCP server for AI agents

Live

OAUTH 2.0

FIELD SERVICE

Productivity

ServiceM8 gives your agent field service operations: create and update jobs and clients, schedule staff, track materials, payments, and checklists, and handle inbox messages, emails, and SMS.

  • Per-user credentials: each call uses the actual user's token, 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.
ServiceM8
agent · Acme Q3
Run
Which jobs are booked for tomorrow and who is assigned?
S
servicem8_list_job_activities
126ms
Field service agent
9 jobs are booked for tomorrow across 4 staff members. Liam has 3, starting with a hot water repair at 8am.
Sources: ServiceM8 job activities, 9 jobs
servicem8
9 jobs
18:29
Message Claude...

Tools your field service agent reaches for on ServiceM8, scoped per user.

CALL ANY TOOL
114 tools for field service in ServiceM8: jobs, clients, contacts, staff allocations, job materials, payments, checklists, notes, tasks, and the inbox, plus email and SMS sending.
servicem8_add_inbox_message_note
Add inbox message note
Add an internal note to a ServiceM8 inbox message. Returns a success flag and a confirmation message. Use to record context on a message before it is converted or archived. Use servicem8_create_note for notes on jobs and other records. Prerequisite: get the message UUID from servicem8_list_inbox_messages.
Parameters
Name
Type
Required
Description
message_uuid
string
Required
UUID of the inbox message. Get UUIDs from the matching list tool.
note
string
Required
Text of the internal note to add to the inbox message.
servicem8_archive_inbox_message
Archive inbox message
servicem8_attach_inbox_message_to_job
Attach inbox message to job
servicem8_create_attachment
Create attachment
servicem8_create_company_contact
Create company contact
servicem8_create_job_allocation
Create job allocation
servicem8_create_job_from_template
Create job from template
servicem8_create_location
Create location
servicem8_delete_client
Delete client
servicem8_get_asset
Get asset
servicem8_get_category
Get category
servicem8_get_feedback
Get feedback
servicem8_get_job_activity
Get job activity
servicem8_get_job_material
Get job material
servicem8_get_knowledge_article
Get knowledge article
servicem8_get_staff_member
Get staff member
servicem8_list_asset_types
List asset types
servicem8_list_categories
List categories
servicem8_list_feedback
List feedback
servicem8_list_job_allocations
List job allocations
servicem8_list_job_payments
List job payments
servicem8_list_knowledge_articles
List knowledge articles
servicem8_list_staff_members
List staff members
servicem8_mark_inbox_message_read
Read mark inbox message
servicem8_search
Search
servicem8_send_email
Send email
servicem8_update_category
Update category
servicem8_update_job
Update job
servicem8_update_job_contact
Update job contact
servicem8_update_location
Update location

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);

// ServiceM8 tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["servicem8"], toolNames: [
    "servicem8_search",
    "servicem8_create_job",
    "servicem8_send_sms"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Create a job for a leaking tap at 12 Smith Street and text the client a confirmation" }] });
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: ["servicem8"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Create a job for a leaking tap at 12 Smith Street and text the client a confirmation" }],
  tools,
});

// Execute the tool call with the user's vaulted ServiceM8 OAuth token
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: ["servicem8"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Create a job for a leaking tap at 12 Smith Street and text the client a confirmation" }],
  tools,
});

// Tool call runs with the user's vaulted ServiceM8 OAuth token
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: ["servicem8"] }, pageSize: 100,
});

const agent = new Agent({
  name: "field_service_agent",
  model: "gemini-2.5-pro",
  instruction: "ServiceM8 tools scoped to this user",
  tools,
});

await agent.run("Create a job for a leaking tap at 12 Smith Street and text the client a confirmation");
Try these prompts
Copy any prompt into your agent. Each maps directly to a ServiceM8 tool. Click to copy, paste into your agent, done.
Jobs
Copy the prompt
Copied
Create a job for a leaking tap at 12 Smith Street for the client Jane Doe.
Copy the prompt
Copied
Find jobs about replacing a hot water system.
Copy the prompt
Copied
Add a diary note to the Hendricks job that parts are on order.
Scheduling and staff
Copy the prompt
Copied
Which jobs are booked for tomorrow and who is assigned?
Copy the prompt
Copied
Allocate the Hendricks job to Liam.
Copy the prompt
Copied
Add a checklist item to inspect the hot water system on the Hendricks job.
Clients and messages
Copy the prompt
Copied
Text Jane Doe that the technician is 20 minutes away.
Copy the prompt
Copied
Convert this inbox message into a new job.
Copy the prompt
Copied
List payments recorded on jobs this week.
SEE HOW AUTH WORKS
Each user signs in to ServiceM8 once, and Scalekit stores and refreshes their tokens. Tokens stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
ServiceM8
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
ServiceM8
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
ServiceM8
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
ServiceM8
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 productivity and operations 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.
Support and Ops Teams
Support ticket automation agent
Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.
Test other agents
See the same per-user auth pattern across other productivity and operations connectors.
GTM
CRM AI agent
Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.
SUPPORT
Support ticket automation (Google ADK)
Fetch, annotate, and archive Zendesk tickets with Notion context, digesting anything it cannot answer to Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared ServiceM8 token looks fine in a demo. In production every job update and SMS 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 token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
ServiceM8 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 ServiceM8 as the user or through a shared service account?
As the user. Each user signs in to ServiceM8 once, and Scalekit stores and refreshes their tokens. Jobs, notes, and messages the agent creates are attributed to that user in your audit trail, not a shared service account.
Where is the ServiceM8 OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in ServiceM8?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the job and client read tools without servicem8_send_sms or servicem8_send_email, which message your clients, or servicem8_delete_job. Scalekit also enforces scope checks before every API call.
What happens when a user revokes ServiceM8 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.
Does deleting a job in ServiceM8 remove it permanently?
No. servicem8_delete_job and servicem8_delete_client archive the record by setting it inactive rather than erasing it, so it disappears from normal use.
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"": {
""servicem8"": {
""url"": ""https://mcp.scalekit.com/servicem8"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.servicem8]
url = ""https://mcp.scalekit.com/servicem8""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""servicem8"": {
""url"": ""https://mcp.scalekit.com/servicem8"",
""type"": ""http""
}
}
}