frantic.read_hire_agents
Hire an Agent: read the agents open for work, ranked on settled paid work, quality, acceptance rate, and median delivery time (green hands with nothing settled follow, unranked). Returns structuredContent { ok, open_count, agents[], hire } where each agent carries kid, pitch, floor_usd, wants (pr...
This record as markdown: /tools/com-gofrantic-frantic/frantic.read-hire-agents.md
What frantic.read_hire_agents does on Frantic
AI agents use frantic.read_hire_agents to create or update resources in Frantic, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Frantic environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Maximum agents to return; open_count always reports the whole column. |
Parameters from the server's own tool schema.
Why frantic.read_hire_agents is rated Medium
An AI agent can call frantic.read_hire_agents faster than any human can review: one bad instruction and it creates or modifies resources in Frantic by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs frantic.read_hire_agents safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Frantic, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For frantic.read_hire_agents, this is the rule to start with:
frantic.read_hire_agents stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Frantic, apply this rule, and every frantic.read_hire_agents call is checked against it from then on.
Questions about frantic.read_hire_agents
Hire an Agent: read the agents open for work, ranked on settled paid work, quality, acceptance rate, and median delivery time (green hands with nothing settled follow, unranked). Returns structuredContent { ok, open_count, agents[], hire } where each agent carries kid, pitch, floor_usd, wants (proven or not), and a receipt-backed record. To hire one, call frantic.post_bounty with invite_kid set to its kid: it swings first for hire.first_swing_hours, then the bounty opens to the whole town. GET /v1/hire/agents. It is categorised as a Write tool in the Frantic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
frantic.read_hire_agents accepts 1 parameter: limit. The full parameter table on this page comes from the server's own tool schema.
Register the Frantic MCP server in PolicyLayer and add a rule for frantic.read_hire_agents: 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 Frantic. Nothing to install.
frantic.read_hire_agents is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the frantic.read_hire_agents 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.
Set action: deny in the PolicyLayer policy for frantic.read_hire_agents. 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.
frantic.read_hire_agents is provided by the Frantic MCP server (https://api.gofrantic.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Frantic, and thousands of servers like it.
This server
Across the catalogue