Skip to main content
Glama

Agent swarm (mixed Antigravity + Codex + Copilot + Cursor, parallel)

agent_swarm

Run multiple tasks in parallel across different AI backends (Antigravity, Codex, Copilot, Cursor) with each worker returning its labeled result.

Instructions

Run SEVERAL tasks IN PARALLEL across ALL backends in a single swarm.

Each task is its own worker and names the backend to run on, so one swarm can mix Antigravity (Gemini), Codex, Copilot, and Cursor workers — they run truly concurrently (capped at max_concurrency) and every answer comes back in one labelled block. A worker that fails is reported in place; the others still return.

SECURITY: this launches N unsandboxed agents at once — N times the prompt-injection surface of a single call (see the module SECURITY note). Only use it with trusted prompts on trusted content.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tasksYesOne object per parallel worker: - backend: "antigravity" (alias "agy"/"gemini"), "codex", "copilot" (alias "gh"/"github"), or "cursor" (required) - prompt: the question or instruction (required) - workspace: working dir for that worker (default: server cwd) - sandbox: Codex/Copilot/Cursor only — "read-only" (default), "workspace-write", or "danger-full-access". Ignored for Antigravity. (Codex's is an enforced OS sandbox; Copilot's and Cursor's are agent/tool-level, not OS boundaries — see copilot_ask / cursor_ask.) - model: optional model override for ANY backend — Codex's `-m`, Copilot's/Cursor's `--model`, or Antigravity's `--model` (an agy label like "Claude Sonnet 4.6 (Thinking)"; validated against each backend's model list). Omit for each backend's default.
watchNoIf true, open the live "Agent Swarm" dashboard window (one row per worker, with a backend badge; click a row for its full step log).
timeout_sNoPer-worker timeout in seconds. Default 180.
max_concurrencyNoMax workers running at once (default 4). Higher = faster but more quota/rate-limit pressure and more agents at once.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Annotations already provide readOnlyHint=false and openWorldHint=true. The description adds critical behavioral details: truly concurrent execution, worker failure handling (reported in place), and a prominent security note about increased prompt-injection surface. This goes well beyond what annotations convey.

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

Conciseness4/5

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

The description is well-structured with a SECURITY section and clear front-loading of purpose. While thorough, it could be slightly more concise; however, every sentence adds value without redundancy.

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

Completeness5/5

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

Given the complexity of a multi-agent swarm tool, the description covers purpose, concurrency model, failure reporting, parameter details, and security risks. With an output schema existing, the description provides sufficient context for correct invocation and risk assessment.

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

Parameters5/5

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

Schema coverage is 100%, but the description enriches each parameter with defaults, aliases, backend-specific behaviors, and security implications. For example, the 'tasks' parameter describes backend aliases, workspace behavior, sandbox meanings, and model override validation. This far exceeds baseline expectation.

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 explicitly states it runs several tasks in parallel across all four backends (Antigravity, Codex, Copilot, Cursor). It distinguishes clearly from sibling tools that are single-backend calls, making the purpose unambiguous.

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?

The description explains when to use this tool (for parallel multi-backend execution) and includes a security warning about untrusted prompts. It does not explicitly state when to use single-backend alternatives, but the context is clear from sibling names.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SinanTufekci/agent-intern'

If you have feedback or need assistance with the MCP directory API, please join our Discord server