ServiceM8 + Claude Code
Build a ServiceM8 reader with Claude Code
Prepare a grounded field-service job briefing
Use Claude Code to build a separate read-only ServiceM8 assistant with Agent200. Ground the field-service job briefing in returned source data.
On this page
Overview
Use Claude Code to implement a read-only ServiceM8 reader in your application. Validate identifiers, schemas and access failures before presenting a field-service job briefing.
Start with one identified job. Preserve returned job status, client identity and scheduled activity details actually returned; report missing data and keep the workflow read-only.
Provider reference: ServiceM8 API.
- Connector
- ServiceM8
- Works with
- Claude Code · Coding agent, with the SDK
- Authentication
- Managed OAuth, per end user
- You need
- An Agent200 API key
- Tools
- 6 tools
- Model in examples
openai/gpt-5.6-sol
Before you start
- An Agent200 API key. Create one on the API keys page of the dashboard.
- ServiceM8 enabled for your project. In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- An end user with a ServiceM8 account. They approve access once, on ServiceM8's own page.
- Claude Code in your project. It writes the code with the Agent200 SDK; you review it.
Connect ServiceM8 to Claude Code
-
1
Step 1: Create your Agent200 API key
Create a key on the API keys page and store it securely.
.envConceptual exampleStore the Agent200 API key as an environment variable # Keep the key out of your code, prompts and chats. export AGENT200_API_KEY="paste-your-key-here" -
2
Step 2: Inspect the real tool definitions
Confirm the actual ServiceM8 read operations and input schemas in your runtime.
-
3
Step 3: Connect the user’s ServiceM8 account
Preserve the same stable user identity during authorization and later requests.
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); } -
4
Step 4: Build and test the read-only answer
Prepare the field-service job briefing only from returned source data. The code example illustrates a sequence, not an SDK installation contract.
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);
Test your connection
Run one request to check everything is wired up.
Ask
Read the ServiceM8 job I identify. Include its returned status, client and scheduled activities. Cite the specific records and disclose missing fields. Do not edit jobs or message anyone.
What should come back
- The selected job is identified.
- Only returned job status, client identity and scheduled activity details actually returned are reported.
- Access gaps and missing context are explicit; no source data is changed.
Check the job and client UUIDs, connected account, OAuth read scopes and schedule window. Report missing or inaccessible records without assuming that no work is scheduled.
Get your API key
Create a key in the Agent200 dashboard. It reaches ServiceM8 and every other connector enabled for your project.
Instructions for AI agents
Using a coding agent? Paste this brief into it, or give it the address of this page. It lists what to do, in order, to connect ServiceM8 to Claude Code.
Goal: connect ServiceM8 to Claude Code with Agent200. Guide: https://www.agent200.com/connectors/servicem8/framework/claude-code/ 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. Make sure ServiceM8 is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs. 3. Add the Agent200 SDK to the project and create a client with that key. 4. Give every request a stable id for the end user. Agent200 uses only that user's own connections. 5. Connect the user's ServiceM8 account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on ServiceM8. 6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "servicem8" in the tools. The model decides when a ServiceM8 tool is needed; Agent200 executes the call. 7. Check it works with this request: "Read the ServiceM8 job I identify. Include its returned status, client and scheduled activities. Cite the specific records and disclose missing fields. Do not edit jobs or message anyone." What should come back: - The selected job is identified. - Only returned job status, client identity and scheduled activity details actually returned are reported. - Access gaps and missing context are explicit; no source data is changed. 8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in ServiceM8, then retry. The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
The whole guide is also available as Markdown, for agents and LLMs: /connectors/servicem8/framework/claude-code.md
ServiceM8 tools Claude Code can call
-
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.
How it works
-
01
Your app sends the request
It calls Agent200 with the model, instructions, the input, the end user's id and the ServiceM8 tools.
-
02
The model picks a tool
The model decides whether a ServiceM8 tool is needed, and with which arguments.
-
03
Agent200 runs the call
It uses that user's own ServiceM8 connection, within the endpoints and scopes your project allows, and returns the result to the model.
-
04
Your app gets the result
Agent200 returns the completed result. Your app decides when the agent runs and what happens next.
Each user's own connection. Connections belong to individual end users. A request for one user never reaches another user's ServiceM8 account.
Permissions at every level. Your project settings decide what the agent may request, the end user decides what they authorize, and ServiceM8 enforces what its API grants.
Troubleshooting
The source cannot be read
Check the job and client UUIDs, connected account, OAuth read scopes and schedule window. Report missing or inaccessible records without assuming that no work is scheduled.
FAQ
How do I verify this result?
Compare the named job and returned job status, client identity and scheduled activity details actually returned with the source. Treat missing information as missing, not as a fact.
Is this a native product integration?
This describes a separate application built with Agent200 and Claude Code; it does not install a connector into the Claude Code app.
