agent-delegate
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-delegateanalyze the current agent state and recommend whether to delegate a read-only investigation"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
agent-delegate
agent-delegate is an MCP-first delegation advisor for coding agents. It helps a main agent decide when to delegate read-only investigation, generate bounded subagent briefs, and summarize subagent results back into compact main-agent context.
Status
This repository implements v1: Read-only Delegation Advisor.
v1 does not execute write-code subagents, edit files on behalf of agents, run background monitoring, or orchestrate worktrees.
Related MCP server: cn-llm-mcp
Install
npm installRun the MCP Server
npm run --silent agent-delegate -- serveConfigure your agent tool to launch that command as a local MCP server.
Check MCP Setup
npm run agent-delegate -- doctordoctor verifies that dependencies are installed, the local MCP server can start, and all five v1 MCP tools are visible through stdio. It also prints a copyable MCP configuration.
Analyze a Sample Agent State
npm run agent-delegate -- analyze examples/agent-state.sample.jsonExpected output includes a recommendation such as:
{
"recommendation": "dispatch_readonly"
}Dogfood Before Release
This project should be dogfooded before any open-source release. Unit tests are not enough because the core product is an MCP tool used by real agents.
Run the MCP smoke test:
npm run smoke:mcpRun realistic fixtures:
npm run check:fixturesSee docs/dogfood.md for the full dogfood protocol.
Generate Rules
npm run agent-delegate -- init codex
npm run agent-delegate -- init claude-code
npm run agent-delegate -- init genericMCP Tools
record_eventassess_delegation_needgenerate_delegation_briefsassess_brief_qualitysummarize_subagent_results
Documentation
Development
npm test
npm run typecheck
npm run buildRoadmap
v1: Read-only Delegation Advisor
v2: Write-readiness Assessor
v3: Controlled Write-agent Delegation
v4: Parallel Write-agent Orchestration
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP delegation fallback for AI agents to discover capabilities, knowledge, tools, and collaborators.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
- AgentdaOAuthcom.myagentda
Agent-native task management: your AI agent is the interface. Delegate to anyone by email.
Remote MCP learning coach for coding agents.
Related MCP Servers
- FlicenseBqualityDmaintenanceAn MCP server that exposes a library of delegation prompts to orchestrate tasks between a primary LLM and specialized sub-agents. It enables the execution of self-contained, bounded tasks with built-in support for configuration discovery and project-specific delegation libraries.3-
- FlicenseAqualityDmaintenanceLocal MCP server that enables delegating low-risk tasks like summarization or code patches to a low-cost model, with the main agent reviewing results.2-
- AlicenseNot gradedqualityCmaintenanceMCP server that enables delegation of small coding implementations to a cheaper language model with propose_patch and apply_patch tools, while the primary agent retains architecture, review, and approval.MIT
- AlicenseNot gradedqualityCmaintenanceAgentPool is a local MCP server that monitors live usage limits of coding-agent subscriptions and allows you to offload work to providers with remaining capacity. It exposes provider, model, and session state, enabling informed manual or agent-driven task delegation.MIT