Compare two topics side-by-side using ASTGL's knowledge base. Returns key points for each topic with source URLs. Great for 'X vs Y' questions.
AI agents call compare_topics to retrieve information from ASTGL Knowledge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
topic_a | string | Yes | First topic (e.g., 'Ollama', 'MCP servers') |
topic_b | string | Yes | Second topic (e.g., 'LM Studio', 'REST APIs') |
Parameters from the server's own tool schema.
This is a query/search operation that reads data from a knowledge base and formats it for comparison. No side effects, no state changes, no destructive operations, no code execution, and no financial transactions are possible. The tool is purely informational retrieval, making it a Read category risk with low severity.
From the tool's definition Tool 'compare_topics' retrieves and presents information side-by-side from a knowledge base with source URLs.
Documented attack patterns abuse exactly the kind of access compare_topics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ASTGL Knowledge, and nothing reaches the server without passing your rules. This is the rule we recommend for compare_topics:
{
"version": "1",
"default": "deny",
"tools": {
"compare_topics": {}
}
}compare_topics 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.
Compare two topics side-by-side using ASTGL's knowledge base. Returns key points for each topic with source URLs. Great for 'X vs Y' questions. It is categorised as a Read tool in the ASTGL Knowledge MCP Server, which means it retrieves data without modifying state.
compare_topics accepts 2 parameters: topic_a, topic_b. Required: topic_a, topic_b. The full parameter table on this page comes from the server's own tool schema.
Register the ASTGL Knowledge MCP server in PolicyLayer and add a rule for compare_topics: 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 ASTGL Knowledge. Nothing to install.
compare_topics 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 compare_topics 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 compare_topics. 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.
compare_topics is provided by the ASTGL Knowledge MCP server (mcp-astgl-knowledge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ASTGL Knowledge, 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.
7 ASTGL Knowledge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.