hve-squad MCP server

Squad Federate

squad_federate

Route requests across named sub-squads in a federated repository, or initialize/promote a federation by adopting an existing squad.

Instructions

Run the squad federation meta layer for a repository that hosts several named sub-squads (for example a product sub-squad for the business team and an azure sub-squad for the architects). Hands the request to the Squad Federation Coordinator, which reads the federation registry (federation.md) and meta-routing (meta-routing.md), selects the target sub-squad(s) — or honors an explicit squad=<name> — and runs each sub-squad's normal per-turn protocol scoped to .copilot-tracking/squad/members/<name>/. Set init to build a federation (propose → confirm → create) on a fresh project, or promote to adopt an existing single squad (a top-level team.md) into a federation as its first sub-squad, relocating its state intact. This is the catch-all federation entry point and runs at the confirm tier with gates. Delegated execution: returns the Federation Coordinator persona, the federation routing decision, and a framed dispatch request for the host to drive. Use for cross-sub-squad requests, an explicit sub-squad target, or federation setup.

Input Schema

TableJSON Schema

Name	Required	Description
`init`	No	When true, run Federation Init Mode (propose → confirm → create) on a fresh project, or Federation Expansion Mode (add a new sub-squad and register it) when a federation already exists, before routing.
`mode`	No	Optional autonomy mode. With a single sub-squad target it is forwarded to that sub-squad's run; with mode=autopilot and no squad= target the Federation Coordinator runs the federation-level autopilot meta-pipeline (ordered sub-squad autopilot runs, aggregated federation gates, one consolidated final-outcome validation).
`tier`	No	Optional model-tier hint forwarded to the selected sub-squad's run.
`owner`	No	Optional Member Name forwarded to the selected sub-squad's run.
`squad`	No	Optional sub-squad name to target directly, overriding meta-routing.
`context`	No	Optional free-form context to frame the federation turn.
`profile`	No	Optional profile hint forwarded to a sub-squad's Init when it has no squad yet.
`promote`	No	When true on an existing single-squad project (a top-level team.md, no federation.md), run Federation Promotion Mode: adopt the existing squad into a federation as its first sub-squad, relocating its state intact, before routing.
`request`	Yes	The work for the federation this turn (routed to one or more sub-squads).
`routing`	No	Optional per-role model routing mode (off, ranked, or manual), forwarded verbatim to every selected sub-squad's coordinator run; each sub-squad persists it in its own team.md and may only narrow it, never widen or substitute it. Ignored on an unattended run.
`discovery`	No	Optional discovery-gate depth, asked once at the federation level and applied per qualifying sub-squad: quick (analyst), standard (designer then analyst), deep (designer, then challenger and experimenter, then analyst), or skip. Each qualifying sub-squad runs its own session and writes its own brief and verdict under its own root. Ignored on an unattended run.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.9.0Oct 7, 2026

addedInput schema / properties / routing

Added value: +{
+  "description": "Optional per-role model routing mode (off, ranked, or manual), forwarded verbatim to every selected sub-squad's coordinator run; each sub-squad persists it in its own team.md and may only narrow it, never widen or substitute it. Ignored on an unattended run.",
+  "enum": [
+    "off",
+    "ranked",
+    "manual"
+  ],
+  "type": "string"
+}

Changed1 schema field changedv0.6.3Aug 19, 2026

addedInput schema / properties / discovery

Added value: +{
+  "description": "Optional discovery-gate depth, asked once at the federation level and applied per qualifying sub-squad: quick (analyst), standard (designer then analyst), deep (designer, then challenger and experimenter, then analyst), or skip. Each qualifying sub-squad runs its own session and writes its own brief and verdict under its own root. Ignored on an unattended run.",
+  "enum": [
+    "quick",
+    "standard",
+    "deep",
+    "skip"
+  ],
+  "type": "string"
+}

Changed2 schema fields changedv0.2.9Jul 28, 2026

changedInput schema / properties / init / description

Previous value: -"When true, run Federation Init Mode (propose → confirm → create) before routing."New value: +"When true, run Federation Init Mode (propose → confirm → create) on a fresh project, or Federation Expansion Mode (add a new sub-squad and register it) when a federation already exists, before routing."

addedInput schema / properties / promote

Added value: +{
+  "description": "When true on an existing single-squad project (a top-level team.md, no federation.md), run Federation Promotion Mode: adopt the existing squad into a federation as its first sub-squad, relocating its state intact, before routing.",
+  "type": "boolean"
+}

Addedv0.2.1Jul 18, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses the confirm-tier gating, that init follows propose → confirm → create, that promote relocates existing squad state intact, and that execution is delegated (returns a persona, a routing decision, and a framed dispatch request rather than doing the work). It does not address permissions, failure/rollback behavior, or what happens when routing selects no sub-squad.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded, but the prose is a dense block with parenthetical examples ('a product sub-squad for the business team and an azure sub-squad for the architects') that do not change how the tool is called, and it repeats init/promote behavior the schema already covers. Sizeable but only partly justified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, annotation-free tool with no output schema, the description covers the essential picture: what gets read (federation.md, meta-routing.md), where state lives, the gated tier, and the delegated return shape. It leaves the interplay of mode/routing/discovery with unattended runs and the dispatch-request format to the schema and host, which is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 11 parameters, including the forwarding semantics and the 'ignored on an unattended run' caveats. The description restates init and promote behavior already present in the schema and adds framing narrative, but no new parameter meaning. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Run the squad federation meta layer for a repository that hosts several named sub-squads') and explicitly positions itself as 'the catch-all federation entry point', which separates it from the narrower squad_run/squad_plan siblings. The init/promote mode behaviors are also stated concretely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit triggers: 'Use for cross-sub-squad requests, an explicit sub-squad target, or federation setup.' That is clear when-to-use guidance, but it never names the sibling tools it should be preferred over or when *not* to use it (e.g. single-squad work should go to squad_run).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Squad Federate

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools