content_compare
Compare the tag profiles of two content entities (franchises or works) and measure how similar they are. Returns a Jaccard similarity score, the list of shared tags, the tags unique to each entity, and a breakdown of shared tags by facet. When to use this tool: an agent needs to compare two franc...
This record as markdown: /tools/io-github-getgapup-mcp-knowledge/content-compare.md
What content_compare does on Mcp Knowledge
AI agents call content_compare to retrieve information from Mcp Knowledge 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 |
|---|---|---|---|
async | boolean | — | If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client ti |
entity_a | string | Yes | Id of the first entity from content_catalog (e.g. 'game-dark-souls', 'music-daft-punk'). |
entity_b | string | Yes | Id of the second entity from content_catalog (e.g. 'game-elden-ring', 'music-justice'). |
entity_type | string | — | Whether both ids are franchises or works (applies to both). Defaults to 'franchise'. |
Parameters from the server's own tool schema.
Why content_compare is rated Low
This is a pure data retrieval and analysis tool. It queries existing tag metadata and computes similarity metrics, which are side-effect-free operations. No data is created, modified, deleted, or external systems are executed. The worst misuse—e.g., an agent comparing unrelated items—causes no harm beyond wasted compute.
From the tool's definition Tool compares tag profiles and returns similarity scores, shared tags, and breakdowns—all read operations that retrieve and analyze existing data without modification.
Attacks that exploit this kind of access
The rule that runs content_compare safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Knowledge, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For content_compare, this is the rule to start with:
content_compare 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 Mcp Knowledge, apply this rule, and every content_compare call is checked against it from then on.
Questions about content_compare
Compare the tag profiles of two content entities (franchises or works) and measure how similar they are. Returns a Jaccard similarity score, the list of shared tags, the tags unique to each entity, and a breakdown of shared tags by facet. When to use this tool: an agent needs to compare two franchises or works (e.g. 'how similar are Dark Souls and Elden Ring?', 'what do Street Fighter and Mortal Kombat have in common?', 'on which axes do these two games differ?'), find positioning overlap, identify cross-sell opportunities, or answer 'if you liked X you might like Y' questions backed by data. Works for any domain (video-games, music, film, tv). It is categorised as a Read tool in the Mcp Knowledge MCP Server, which means it retrieves data without modifying state.
content_compare accepts 4 parameters: async, entity_a, entity_b, entity_type. Required: entity_a, entity_b. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Knowledge MCP server in PolicyLayer and add a rule for content_compare: 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 Mcp Knowledge. Nothing to install.
content_compare 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 content_compare 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 content_compare. 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.
content_compare is provided by the Mcp Knowledge MCP server (https://mcp.gapup.io). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Knowledge, and thousands of servers like it.
This server
Across the catalogue