Score a specific title against a user's taste profile and explain the alignment. Use when the user asks "why would I like this?", "is this for me?", or wants to know how well a specific anime/manga matches their preferences. Returns match score, genre/theme affinity breakdown, mood fit, and exist...
Single-target operation
Part of the Ani MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call anilist_explain to retrieve information from Ani without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though anilist_explain only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
anilist_explain:
rules:
- action: allowSee the full Ani policy for all 55 tools.
Agents calling read-class tools like anilist_explain have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Score a specific title against a user's taste profile and explain the alignment. Use when the user asks "why would I like this?", "is this for me?", or wants to know how well a specific anime/manga matches their preferences. Returns match score, genre/theme affinity breakdown, mood fit, and existing list status.. It is categorised as a Read tool in the Ani MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for anilist_explain. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Ani MCP server.
anilist_explain 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 anilist_explain rule in your Intercept 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 Intercept policy for anilist_explain. 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.
anilist_explain is provided by the Ani MCP server (ani-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept