Identify sponsor segments in a podcast episode and estimate read-through rates. Returns sponsor list, read type (host-read, mid-roll, etc.), call-to-action, and aggregate metrics. Uses cached extraction if episode_id was previously processed.
Handles credentials or secrets (api_key)
Part of the Podcast Commerce Intelligence MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call analyze_episode_sponsors to retrieve information from Podcast Commerce Intelligence 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 analyze_episode_sponsors 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:
analyze_episode_sponsors:
rules:
- action: allowSee the full Podcast Commerce Intelligence policy for all 5 tools.
Agents calling read-class tools like analyze_episode_sponsors 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.
Identify sponsor segments in a podcast episode and estimate read-through rates. Returns sponsor list, read type (host-read, mid-roll, etc.), call-to-action, and aggregate metrics. Uses cached extraction if episode_id was previously processed.. It is categorised as a Read tool in the Podcast Commerce Intelligence MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for analyze_episode_sponsors. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Podcast Commerce Intelligence MCP server.
analyze_episode_sponsors 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 analyze_episode_sponsors 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 analyze_episode_sponsors. 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.
analyze_episode_sponsors is provided by the Podcast Commerce Intelligence MCP server (sincetoday/podcast-commerce-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