hve-squad MCP server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SQUAD_MCP_WORKER_ENABLED | No | Enable background worker ACA Job for long runs. | false |
| SQUAD_MCP_RUN_STATE_BACKEND | No | Backend for run state storage: 'file' (local) or 'table' (Azure Table Storage). | file |
| SQUAD_MCP_ENABLE_RENDER_PPTX | No | Opt-in to enable the squad_render_pptx tool for PPTX rendering. | false |
| SQUAD_MCP_REMOTE_PIPELINE_ENABLED | No | Enable the async advisory pipeline (squad_run, squad_status). Defaults to false. | false |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| squad_researchA | Run the squad's research stage on a question or codebase. Routes to the Squad Researcher (squad |
| squad_planA | Run the squad's planning stage. Routes to the Squad Lead (squad |
| squad_reviewA | Run the squad's review stage. Routes to the Squad Reviewer (squad |
| squad_architectA | Run the squad's architecture stage. Routes to the System Architecture Reviewer (squad |
| squad_runA | Run the full squad pipeline for any request. Hands the request to the Squad Coordinator, which classifies it against the routing table and dispatches the matched roles through Research -> Plan -> Implement -> Review, carrying the council Implementation Gate, the autopilot/autonomous Human Gates, and the notification approval contract unchanged. This is the catch-all entry point and runs at the |
| squad_federateA | Run the squad federation meta layer for a repository that hosts several named sub-squads (for example a |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each stage tool focuses on a distinct phase (research, plan, review, architect) and the descriptions provide clear 'use for' cues. The main overlap risk is between squad_review and squad_architect, or between a stage tool and squad_run, but the intended scope is made explicit enough for an agent to select correctly.
All tools follow a consistent squad_<action> pattern in lowercase snake_case. The verbs (research, plan, review, architect, run, federate) are uniform in style, even if 'architect' is used as a verb, and the prefix makes the family relationship obvious.
Six tools is well within the ideal range for a workflow-orchestration server. Each tool covers a distinct stage or meta-operation, and there is no obvious bloat or redundancy; the count feels properly scoped for the stated purpose.
The tool set covers research, planning, review, architecture, the full pipeline, and federation setup. However, the squad_run description mentions an 'Implement' stage that has no corresponding standalone tool, which is a minor gap if a caller wants to run only that phase. Overall core workflows are still complete.