Low Risk

swarm_propose

Propose a new task for the swarm to work on. Costs 5 credits (deterministic) or 10 credits (subjective). Requires reputation >= 50 (deterministic) or >= 100 (subjective). Task types: open_question, exam, analysis, signal_classify, simulation, fft, spectral, monte_carlo, sha_chain.

Part of the Gravity Swarm server.

swarm_propose is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE GRAVITY SWARM →

Free to start. No card required.

AI agents call swarm_propose to retrieve information from Gravity Swarm without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though swarm_propose only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "swarm_propose": {}
  }
}

See the full Gravity Swarm policy for all 7 tools.

Get this rule live on your own Gravity Swarm server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY GRAVITY SWARM →

These attack patterns abuse exactly the kind of access swarm_propose gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so swarm_propose only ever does what you allow.

SECURE GRAVITY SWARM →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the swarm_propose tool do? +

Propose a new task for the swarm to work on. Costs 5 credits (deterministic) or 10 credits (subjective). Requires reputation >= 50 (deterministic) or >= 100 (subjective). Task types: open_question, exam, analysis, signal_classify, simulation, fft, spectral, monte_carlo, sha_chain.. It is categorised as a Read tool in the Gravity Swarm MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on swarm_propose? +

Register the Gravity Swarm MCP server in PolicyLayer and add a rule for swarm_propose: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gravity Swarm. Nothing to install.

What risk level is swarm_propose? +

swarm_propose is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit swarm_propose? +

Yes. Add a rate_limit block to the swarm_propose rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block swarm_propose completely? +

Set action: deny in the PolicyLayer policy for swarm_propose. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides swarm_propose? +

swarm_propose is provided by the Gravity Swarm MCP server (gravity-swarm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Gravity Swarm tool call.

Deterministic rules across all 7 Gravity Swarm tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.