Sonnet 5 Agent
Server Details
Authenticated async Sonnet 5 Agent agent with status polling and artifact results.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: metadata (agent_info), creation (create_run), cancellation (cancel_run), polling (get_run_status), and result retrieval (get_run_result). There is no overlap between status and result, and the descriptions explicitly clarify the workflow.
All tools use a consistent 'agentfarm_' prefix and snake_case. The verb patterns are mostly consistent (cancel_run, create_run, get_run_status, get_run_result), with the minor exception of 'agent_info' which omits a verb like 'get'.
Five tools perfectly cover the async run lifecycle without redundancy. Each tool earns its place, and the count is well within the ideal 3–15 range for this domain.
The core run lifecycle (create, status, result, cancel) plus agent info is covered. A minor gap is the absence of a way to list existing runs or discover run IDs, which could force agents to track them externally.
Available Tools
5 toolsagentfarm_agent_infoGet Sonnet 5 Agent access informationARead-onlyIdempotentInspect
Returns this agent's identity, listed per-task price, MCP endpoint, and access URL. This metadata call does not run the model and does not require a bearer token; execution consumes prepaid run units.
Inputs: no named parameters.
agentfarm_cancel_runCancel AgentFarm runADestructiveIdempotentInspect
Cancels an authenticated queued or running run.
Inputs: run_id (required).
agentfarm_create_runCreate a Sonnet 5 Agent runAInspect
Queues an authenticated asynchronous task. This can consume paid model capacity. Poll with agentfarm_get_run_status, then read agentfarm_get_run_result.
Inputs: task (required), task_input, idempotency_key.
agentfarm_get_run_resultGet AgentFarm run resultARead-onlyIdempotentInspect
Returns the final summary and artifact download URLs for an authenticated run.
Inputs: run_id (required).
agentfarm_get_run_statusGet AgentFarm run statusARead-onlyIdempotentInspect
Returns queued, running, succeeded, or failed status for an authenticated run.
Inputs: run_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Authenticated async Opus 5.5 agent with status polling and artifact results.
Authenticated async GPT-5.6-sol Agent agent with status polling and artifact results.
Authenticated async GPT-5.6-luna Agent agent with status polling and artifact results.
Authenticated async Fable 5 Agent agent with status polling and artifact results.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceConnects AI assistants to an AgentX account so they can list and inspect a fleet of AI coding agents running on the user's own machines, read their output, send them messages, create chats, wait for events, and retrieve artifacts. Sign-in happens through browser-based OAuth, with no API key or local install required.MIT- FlicenseNot gradedqualityDmaintenanceEnables delegation of agentic sessions to Kubernetes-hosted Claude agents running on the Ambient Code Platform. Supports creating, managing, and communicating with remote AI agent sessions through OpenShift authentication.-
- AlicenseNot gradedqualityCmaintenanceEnables a remote AI agent to delegate synchronous or asynchronous tasks to a self-hosted Hermes agent over MCP Streamable HTTP, follow run status, retrieve durable results, and inspect artifacts.MIT
- FlicenseAqualityDmaintenanceDelegates expensive or long-running AI tasks to Kubernetes-hosted Claude agents running on OpenShift. Enables creating, managing, and monitoring remote agentic sessions for complex work like codebase analysis and security audits.41-
Glama MCP Gateway
Add one secure layer between your agents and this server.