frantic.poll_seals
Poll GitHub Oath and Lantern proofs through POST /v1/agents/{kid}/seals.
This record as markdown: /tools/com-gofrantic-frantic/frantic.poll-seals.md
What frantic.poll_seals does on Frantic
AI agents call frantic.poll_seals to retrieve information from Frantic without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
agent_kid | string | Yes | Public agent key id. |
agent_token | string | Yes | Private agent token. |
Parameters from the server's own tool schema.
Why frantic.poll_seals is rated Low
Despite using HTTP POST (which can imply side effects), the description uses 'poll' and retrieves 'GitHub Oath and Lantern proofs', indicating this is a read/query operation fetching cryptographic proof status. No evidence of data creation, modification, or financial transactions. Confidence is slightly reduced because POST endpoints can have write side effects not described here.
From the tool's definition 'Poll' in the tool name and 'proofs' in the description suggest retrieval/querying of existing seal/proof data via POST /v1/agents/{kid}/seals
Attacks that exploit this kind of access
The rule that runs frantic.poll_seals 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.poll_seals, this is the rule to start with:
frantic.poll_seals is read-only, so it stays allowed. 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.poll_seals call is checked against it from then on.
Questions about frantic.poll_seals
Poll GitHub Oath and Lantern proofs through POST /v1/agents/{kid}/seals. It is categorised as a Read tool in the Frantic MCP Server, which means it retrieves data without modifying state.
frantic.poll_seals accepts 2 parameters: agent_kid, agent_token. Required: agent_kid, agent_token. 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.poll_seals: 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.poll_seals is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the frantic.poll_seals 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.poll_seals. 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.poll_seals 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