CRM and sales
ServiceM8 for AI agents.
Put the next job in context.
Read accessible ServiceM8 jobs, clients, contacts and scheduled activities. Prepare a grounded field-service job briefing.
About ServiceM8
With the ServiceM8 connector, your agent reads jobs and clients in each user’s own ServiceM8 account. It can list jobs, read a job, look up clients and their contacts, and list the activities on a job, using only the tools your project allows.
ServiceM8 is a job management app for field service businesses.
Tools
What your agent can do in ServiceM8.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own ServiceM8 connection.
-
List jobs
Readservicem8_list_jobsFind accessible jobs and their returned status and client references.
-
Read a job
Readservicem8_get_jobRetrieve details of one identified job.
-
List clients
Readservicem8_list_clientsFind client records available to the connected account.
-
Read a client
Readservicem8_get_clientRetrieve one identified client record.
-
List client contacts
Readservicem8_list_client_contactsFind contacts associated with an identified client.
-
List scheduled activities
Readservicem8_list_job_activitiesRead scheduled job activities within the available scope.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in ServiceM8, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read jobs and clients, and switch off
servicem8_list_job_activitiesif it should not see scheduled activities. -
Restrict what the agent reaches
Choose the endpoints and scopes a project may use, for example jobs and clients but not job activities. A call outside them is refused.
Get started
Connect ServiceM8
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect ServiceM8
Each end user authorizes their own ServiceM8 account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own ServiceM8 account, once. const connection = await agent200 .user("user_123") .connect("servicem8"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the ServiceM8 tools
Name the user, the model and the tools. The model decides which ServiceM8 tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "List the open jobs for Hamilton Plumbing", tools: ["servicem8"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Connect the intended ServiceM8 account
Authorize ServiceM8 through managed OAuth and select the account that holds the requested job.
-
Grant only the read scopes needed
The job, customer, customer-contact and schedule reads use separate ServiceM8 OAuth scopes. Access follows the connected account.
-
Keep account and staff identity distinct
ServiceM8 userInfo uuid and name identify the account, not the staff member who authorized OAuth. Preserve the authenticated application user separately.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the ServiceM8 connector and how to use it.
Connector: ServiceM8, through Agent200. In code: "servicem8". What it does: Read accessible ServiceM8 jobs, clients, contacts and scheduled activities. Prepare a grounded field-service job briefing. Page: https://www.agent200.com/connectors/servicem8/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on ServiceM8's own page, through the authorization link Agent200 returns. Never ask a user for a ServiceM8 password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: servicem8_list_jobs, servicem8_get_job, servicem8_list_clients, servicem8_get_client, servicem8_list_client_contacts, servicem8_list_job_activities. Name "servicem8" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/servicem8/framework/claude/ https://www.agent200.com/connectors/servicem8/framework/chatgpt/ https://www.agent200.com/connectors/servicem8/framework/claude-code/ https://www.agent200.com/connectors/servicem8/framework/muse/ https://www.agent200.com/connectors/servicem8/framework/grok-bot/ https://www.agent200.com/connectors/servicem8/framework/openai-dots/ https://www.agent200.com/connectors/servicem8/framework/claude-duet/ https://www.agent200.com/connectors/servicem8/framework/hermes-agent/ https://www.agent200.com/connectors/servicem8/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/servicem8.md
Guides
Use ServiceM8 with the AI you build on.
Step-by-step setup for ServiceM8 with a specific model, assistant or agent framework.
-
ServiceM8 + Claude
How to connect ServiceM8 to Claude
-
ServiceM8 + ChatGPT
How to connect ServiceM8 to ChatGPT
-
ServiceM8 + Claude Code
How to connect ServiceM8 to Claude Code
-
ServiceM8 + Muse
How to connect ServiceM8 to Muse
-
ServiceM8 + Grok Bot
How to connect ServiceM8 to Grok Bot
-
ServiceM8 + OpenAI Dots
How to connect ServiceM8 to OpenAI Dots
-
ServiceM8 + Claude Duet
How to connect ServiceM8 to Claude Duet
-
ServiceM8 + Hermes Agent
How to connect ServiceM8 to Hermes Agent
-
ServiceM8 + OpenClaw
How to connect ServiceM8 to OpenClaw
FAQ
ServiceM8 and Agent200, answered.
Which job should the agent use?
Select a returned job UUID, then check the related client UUID and status. A similar job title or client name is not enough to identify the record. ServiceM8 jobs reference.
Does a schedule result show every booking?
No. List job activities for the relevant scope, follow available pagination and state the period and job actually read. ServiceM8 maps scheduled bookings to JobActivity records. Job activities reference.
Can the agent change a job or contact the client?
The listed operations read records. A proposed action in the briefing does not update ServiceM8 or send a customer message.
Does userInfo identify the authorizing staff member?
No. Its uuid and name identify the ServiceM8 account. Do not attribute a booking or change to a staff member from that response.
Which permissions matter?
Check read_jobs, read_customers, read_customer_contacts and read_schedule as needed, plus actual account access. Confirm runtime tool names and input schemas before calling.