Filter topics with a concise query language: use key:value tokens separated by spaces; category/categories for categories (comma = OR, '=category' = without subcats, '-' prefix = exclude), tag/tags (comma = OR, '+' = AND) and tag_group; status:(open|closed|archived|listed|unlisted|public) and per...
Part of the Discource Mcp Tools MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call discourse_filter_topics to retrieve information from Discource Mcp Tools 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 discourse_filter_topics 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:
discourse_filter_topics:
rules:
- action: allowSee the full Discource Mcp Tools policy for all 15 tools.
Agents calling read-class tools like discourse_filter_topics 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.
Filter topics with a concise query language: use key:value tokens separated by spaces; category/categories for categories (comma = OR, '=category' = without subcats, '-' prefix = exclude), tag/tags (comma = OR, '+' = AND) and tag_group; status:(open|closed|archived|listed|unlisted|public) and personal in:(bookmarked|watching|tracking|muted|pinned); dates: created/activity/latest-post-(before|after) with YYYY-MM-DD or N (days); numeric: likes[-op]-(min|max), posts-(min|max), posters-(min|max), views-(min|max); order: activity|created|latest-post|likes|likes-op|posters|title|views|category with optional -asc; free text terms are matched full-text. Results are permission-aware.. It is categorised as a Read tool in the Discource Mcp Tools MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for discourse_filter_topics. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Discource Mcp Tools MCP server.
discourse_filter_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 discourse_filter_topics 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 discourse_filter_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.
discourse_filter_topics is provided by the Discource Mcp Tools MCP server (king-of-the-grackles/discourse-forum-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