Search talks by keyword across titles, descriptions, speaker names, and tags (e.g.
AI agents call find_talks_by_topic to retrieve information from CityJS London 2026 Companion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The find_talks_by_topic tool retrieves and filters conference talk information based on search parameters. This is a classic Read operation: it queries existing data without side effects, does not modify or delete records, and does not execute code or trigger financial transactions.
From the tool's definition Tool searches talks by keyword across titles, descriptions, speaker names, and tags — a query operation with no data modification, deletion, or execution of external code.
Documented attack patterns abuse exactly the kind of access find_talks_by_topic gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CityJS London 2026 Companion, and nothing reaches the server without passing your rules. This is the rule we recommend for find_talks_by_topic:
{
"version": "1",
"default": "deny",
"tools": {
"find_talks_by_topic": {}
}
}find_talks_by_topic 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.
Search talks by keyword across titles, descriptions, speaker names, and tags (e.g. It is categorised as a Read tool in the CityJS London 2026 Companion MCP Server, which means it retrieves data without modifying state.
Register the CityJS London 2026 Companion MCP server in PolicyLayer and add a rule for find_talks_by_topic: 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 CityJS London 2026 Companion. Nothing to install.
find_talks_by_topic 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 find_talks_by_topic 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 find_talks_by_topic. 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.
find_talks_by_topic is provided by the CityJS London 2026 Companion MCP server (tejasq/basically-mcp-apps). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CityJS London 2026 Companion, 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.
4 CityJS London 2026 Companion tools catalogued and risk-classified — across an index of 43,000+ MCP servers.