List agents and their capabilities in a project. Manager only.
AI agents call discover_agents to retrieve information from Writbase without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about agents and their capabilities without creating, modifying, deleting, or executing anything. It is a straightforward query operation with no side effects, making it a Read category risk. The 'Manager only' permission qualifier is a security control that reduces likelihood of abuse but does not alter its category.
From the tool's definition 'List agents and their capabilities' – no modification, deletion, or execution described. The manager-only restriction indicates access control but does not change the tool's fundamental behavior: it retrieves and queries information only.
Documented attack patterns abuse exactly the kind of access discover_agents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Writbase, and nothing reaches the server without passing your rules. This is the rule we recommend for discover_agents:
{
"version": "1",
"default": "deny",
"tools": {
"discover_agents": {}
}
}discover_agents is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List agents and their capabilities in a project. Manager only. It is categorised as a Read tool in the Writbase MCP Server, which means it retrieves data without modifying state.
Register the Writbase MCP server in PolicyLayer and add a rule for discover_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 Writbase. Nothing to install.
discover_agents 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 discover_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 discover_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.
discover_agents is provided by the Writbase MCP server (https://{PROJECT_REF}.supabase.co/functions/v1/mcp-server/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Writbase, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Writbase tools catalogued and risk-classified — across an index of 43,000+ MCP servers.