mcp-swarm-router
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_SWARM_AGY_CMD | No | Optional override for the agy CLI command. If not set, defaults to 'agy' on PATH. | |
| MCP_SWARM_CODEX_CMD | No | Optional override for the codex CLI command. If not set, defaults to 'codex' on PATH. | |
| MCP_SWARM_CLAUDE_CMD | No | Optional override for the claude CLI command. If not set, defaults to 'claude' on PATH. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_agent_rosterA | Returns the list of local agents available for delegation, each with its id and specialization. Call this before delegate_task to decide which agent_name fits a given subtask. |
| delegate_taskA | Spawns the named agent's CLI in workspace_path with the given prompt, waits for it to finish, and returns its stdout/stderr/exit code. Use get_agent_roster first to pick the right agent_name. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| plan-and-delegate | Guides the host LLM through breaking a large task into subtasks and routing each to the right local agent. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one provides an inventory of available agents, the other executes a task with a specified agent. There is no overlap or ambiguity between them.
Both tool names follow a consistent verb_noun pattern (get_agent_roster, delegate_task), using snake_case and clear action verbs. The naming is uniform and predictable.
With only 2 tools, the set is on the thin side but still covers the core workflow of a router: discovering agents and delegating to them. It feels slightly sparse for a 'swarm' concept, but each tool is essential.
The tool pair covers the full delegation lifecycle needed: learn who is available, then execute a task. Missing features like parallel delegation or cancellation are minor gaps for a simple router implementation, and agents can work around them by calling delegate_task repeatedly.