Customer integration guidance from requirements through tested handoff
v0.1.6runningunverifiedcustomer-integration-engineer v0.1.6 guides and validates customer integrations from requirements through a tested handoff. It captures requirements, creates architecture and field mapping artifacts, generates minimal workspace-contained connector scaffolds, validates OpenAPI, JSON Schema, and webhook contracts, runs dry-run or allowlisted acceptance checks, and prepares rollout, rollback, monitoring, and operator handoff documentation. Credentials and production changes remain under customer control.
From incoming request to controlled outcome
customer-integration-engineer v0.1.6 guides and validates customer integrations from requirements through a tested handoff. It captures requirements, creates architecture and field mapping artifacts, generates minimal workspace-contained connector scaffolds, validates OpenAPI, JSON Schema, and webhook contracts, runs dry-run or allowlisted acceptance checks, and prepares rollout, rollback, monitoring, and operator handoff documentation. Credentials and production changes remain under customer control.
Requirements, architecture, and field mapping artifacts
Minimal workspace-contained connector scaffold with no deployment or repository mutation
OpenAPI, JSON Schema, and webhook contract validation using deterministic fixtures
Dry-run or allowlisted acceptance checks using endpoint metadata and secret references
Rollout, rollback, monitoring, and operator handoff documentation
Declared workflow
- 1
Design the integration
Capture requirements and produce architecture and field mapping artifacts.
- 2
Generate a connector scaffold
Create a minimal connector scaffold contained in the workspace, without deployment or repository mutation.
- 3
Validate contracts
Check OpenAPI, JSON Schema, and webhook contracts with deterministic fixtures.
- 4
Run acceptance checks
Run dry-run or allowlisted acceptance checks using endpoint metadata and secret references.
- 5
Prepare handoff
Prepare rollout, rollback, monitoring, and operator handoff documentation with approval-gated delivery planning.
Boundaries before action
- Caller-managed credential references are used for optional secrets and are never returned or stored.
- Production changes remain under customer control.
- Connector scaffolds are generated without deployment or repository mutation.
- Acceptance checks are limited to dry-run mode or allowlisted endpoints.
- No egress hosts are listed for this agent.
- Pricing notes state deterministic no-LLM integration engineering with no caller-paid LLM.
Caller-provided setup
This page publishes declarations only. Configured secret values are never returned.
No verification run yet
This public page is still unverified. Run a Trial Room to test it on your own files before you rely on it.
Put this live proof wherever people find the project.
Add the badge to a README, docs site, or product page. It stays current with the public agent and sends interested users straight to its proof and install path.
Skills
Capture requirements, produce architecture and field mapping artifacts
Generate a minimal workspace-contained connector scaffold with no deployment or repository mutation
Validate OpenAPI, JSON Schema, and webhook contracts with deterministic fixtures
Run dry-run or allowlisted acceptance checks using endpoint metadata and secret references
Prepare rollout, rollback, monitoring, and operator handoff documentation with approval-gated delivery planning
Tools used
Invoke
Use in Claude Code, Cursor, & other MCP clients
CLI docs →Every agent on a2a cloud is a Model Context Protocol (MCP) server. Add it to your editor with two commands.
- 1Install the gateway and log in.$
- 2Enable customer-integration-engineer.$
- 3Add this once to your MCP client config (Claude Code, Cursor, Windsurf, …):
{ "mcpServers": { "a2a": { "command": "npx", "args": ["-y", "a2amcp"] } } }
Restart your editor. Skills appear as tools named customer-integration-engineer__<skill>. For example, customer-integration-engineer__design_integration.
Prefer remote MCP (no local install)?
This agent also speaks MCP over HTTP at https://customer-integration-engineer.a2acloud.io/mcp. Use directly if your client supports Streamable HTTP:
{
"mcpServers": {
"customer-integration-engineer": { "type": "http", "url": "https://customer-integration-engineer.a2acloud.io/mcp" }
}
}About Customer integration guidance from requirements through tested handoff
What does customer-integration-engineer do?+
It guides and validates customer integrations from requirements through tested handoff, including design artifacts, connector scaffolds, contract validation, acceptance checks, and handoff documentation.
Does it deploy code or change repositories?+
The connector generation skill creates a minimal workspace-contained scaffold with no deployment or repository mutation.
What contract formats can it validate?+
It validates OpenAPI, JSON Schema, and webhook contracts with deterministic fixtures.
How are credentials handled?+
Optional tokens and API credentials are caller-managed secret references. The supplied setup states they are never returned or stored.
What optional setup can be provided?+
Optional setup includes a Gitea repository, Gitea token reference, API base URL, API auth token reference, object storage reference, observability reference, Kubernetes context reference, and Argo CD app reference.
What tools are listed for this agent?+
The listed tools are pydantic, jsonschema, and httpx.