resolve_actor
Resolve the actor class and channel. Classes: authorized_trading_partner and its members (manufacturer · repackager · wholesale_distributor · dispenser · third_party_logistics_provider; cosmetic_responsible_person · nhp_licence_holder on the non-drug pathways), prescriber, the referral classes pa...
This record as markdown: /tools/a2a-peptides/resolve-actor.md
What resolve_actor does on A2A-Peptides
AI agents use resolve_actor to create or update resources in A2A-Peptides, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A2A-Peptides environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
credential | object | — | |
actor_class | string | Yes |
Parameters from the server's own tool schema.
Why resolve_actor is rated Medium
An AI agent can call resolve_actor faster than any human can review: one bad instruction and it creates or modifies resources in A2A-Peptides by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs resolve_actor safely
PolicyLayer is an MCP gateway: it sits between your AI agents and A2A-Peptides, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For resolve_actor, this is the rule to start with:
resolve_actor 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 A2A-Peptides, apply this rule, and every resolve_actor call is checked against it from then on.
Questions about resolve_actor
Resolve the actor class and channel. Classes: authorized_trading_partner and its members (manufacturer · repackager · wholesale_distributor · dispenser · third_party_logistics_provider; cosmetic_responsible_person · nhp_licence_holder on the non-drug pathways), prescriber, the referral classes patient and public, and agent (inherits the class of the credential it presents; none returns DENY_UNLICENSED_AGENT). Returns communication_class: trade_information or public. It is categorised as a Write tool in the A2A-Peptides MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
resolve_actor accepts 2 parameters: credential, actor_class. Required: actor_class. The full parameter table on this page comes from the server's own tool schema.
Register the A2A-Peptides MCP server in PolicyLayer and add a rule for resolve_actor: 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 A2A-Peptides. Nothing to install.
resolve_actor 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 resolve_actor 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 resolve_actor. 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.
resolve_actor is provided by the A2A-Peptides MCP server (https://mcp.a2a-peptides.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on A2A-Peptides, and thousands of servers like it.
This server
Across the catalogue