MCP server that lets Claude Code agents delegate tasks to agents in other project directories
Connect Agent to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server that lets Claude Code agents delegate tasks to agents in other project directories. The agent mcp server is what makes that connection.
Each agent runs as a separate claude -p session in its own project directory — inheriting that project's MCP servers, CLAUDE.md, and tools. The calling agent just gets the result back.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
list_agents — Lists all configured agents. Call this first to see what's availableinspect_agent — Cheap detailed lookup — reads the agent's files without spawning a claude session. Returns the full config (timeout, model, budget, permission modeGroups — A group bundles related agents into a cross-project working set — typically a few code repos plus capability gateways (an infra agent with adispatch — One-shot task delegation. Results are cached — identical requests within TTL return instantlydispatch_session — Multi-turn: continue a conversation with an agent. First call starts a session, pass session_id back to continue. Never cacheddispatch_parallel — Run multiple tasks concurrently. Much faster than sequential dispatch callsdispatch_stream — Same as dispatch but shows live progress while the agent works. Use for long-running tasks. Not cacheddispatch_dialogue — Two agents collaborate through multi-turn conversation. Never cachedadd_agent — Register a new project directory as an agent. Description is auto-generated from project files if omittedupdate_agent — Update an existing agent's configuration. Only non-empty fields are changed. Pass "none" to clear a fieldremove_agent — The remove_agent tool exposed by this serveragent-dispatch on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agent's toolset — list_agents, inspect_agent, Groups and 8 more — is a fair guide to whether it matches your workflow. It is maintained by ginkida; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| list_agents | Lists all configured agents. **Call this first** to see what's available. |
| inspect_agent | Cheap detailed lookup — reads the agent's files without spawning a claude session. Returns the full config (timeout, model, budget, permission mode, allowed/disallowed tools), detected MCP/stacks/DBs, plus short previews |
| Groups | A **group** bundles related agents into a cross-project working set — typically a few code repos plus capability gateways (an infra agent with a Portainer MCP, an analytics agent with a browser + Yandex Metrica). It lets |
| dispatch | One-shot task delegation. Results are cached — identical requests within TTL return instantly. |
| dispatch_session | Multi-turn: continue a conversation with an agent. First call starts a session, pass session_id back to continue. Never cached. |
| dispatch_parallel | Run multiple tasks concurrently. Much faster than sequential dispatch calls. |
| dispatch_stream | Same as dispatch but shows live progress while the agent works. Use for long-running tasks. Not cached. |
| dispatch_dialogue | Two agents collaborate through multi-turn conversation. Never cached. |
| add_agent | Register a new project directory as an agent. Description is auto-generated from project files if omitted. |
| update_agent | Update an existing agent's configuration. Only non-empty fields are changed. Pass "none" to clear a field. |
| remove_agent | The remove_agent tool exposed by this server. |
{
"mcpServers": {
"agent-dispatch": {
"command": "uvx",
"args": ["agent-dispatch"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.