# Frazer API, MCP and errors

> One API behind the console, the CLI, the MCP server and the Terraform provider: REST and gRPC from the protobuf contracts, the MCP server at mcp.frazer.ai, every error reason with its fix, the events webhooks deliver and the Terraform and OpenTofu resources.

Part of Frazer's docs for agents. Every page on frazer.ai: https://frazer.ai/llms.txt. Every docs page: https://frazer.ai/docs/llms.txt.

## How agents should use Frazer API, MCP and errors

- Prefer the MCP server or the CLI to hand-written HTTP calls: they carry auth, retries, plans and approvals.
- MCP tools read by default; a write becomes a plan that waits for a person's approval.
- Branch on an error's reason, such as `QUOTA_EXCEEDED`, not on its message, and apply the fix the Errors page gives.
- Plan every write first: `validate_only` in the API, `--dry-run` in the CLI. Both run every check and change nothing.

## Pages

- [API](https://frazer.ai/docs/api.md?from=llms-txt): The Frazer API on api.frazer.ai, REST, gRPC and Connect from one set of protobuf contracts, with resource names, plans, long-running operations, idempotent retries, pagination, rate limits and one error model.
- [MCP](https://frazer.ai/docs/mcp.md?from=llms-txt): Connect Claude, Codex, your editor's agent or any MCP client to Frazer at mcp.frazer.ai, with OAuth sign-in, scopes and toolsets, read-only by default, and writes that become plans a person approves.
- [Errors](https://frazer.ai/docs/errors.md?from=llms-txt): How Frazer reports errors in the API, CLI, MCP and console, with status codes, reasons, decision IDs you can replay, remedies and Request access, and every error reason with its fix.
- [Webhooks and events](https://frazer.ai/docs/webhooks.md?from=llms-txt): Signed events out of Frazer. CloudEvents-shaped JSON for every change, delivered to your endpoints with Standard Webhooks signatures, retries for about 3 days and a 30-day delivery log.
- [Terraform and OpenTofu](https://frazer.ai/docs/terraform.md?from=llms-txt): Manage Frazer resources as code with the frazer-ai/frazer provider for Terraform and OpenTofu, with authentication, imports, secrets kept out of state, and plans that show quota, policy and cost.

## Optional

- [Full text of these pages](https://frazer.ai/docs/api/llms-full.txt): 5 pages, 94,812 characters, about 23,703 tokens