USE THIS TOOL when the user asks about a specific software product - its pricing, features, platforms, who it's for, or how actively it's maintained. Triggers: "tell me about X", "what is X", "how much does X cost", "what platforms does X support", "is X actively maintained", "X pricing". Returns...
Single-target operation
Part of the PeerPush MCP MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call peerpush_product_details to retrieve information from PeerPush MCP 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 peerpush_product_details 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:
peerpush_product_details:
rules:
- action: allowSee the full PeerPush MCP policy for all 8 tools.
Agents calling read-class tools like peerpush_product_details 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.
USE THIS TOOL when the user asks about a specific software product - its pricing, features, platforms, who it's for, or how actively it's maintained. Triggers: "tell me about X", "what is X", "how much does X cost", "what platforms does X support", "is X actively maintained", "X pricing". Returns comprehensive product data including pricing, platforms, use cases, target audiences, alternatives, active discount codes, community metrics, and recent development updates.. It is categorised as a Read tool in the PeerPush MCP MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for peerpush_product_details. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the PeerPush MCP MCP server.
peerpush_product_details 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 peerpush_product_details 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 peerpush_product_details. 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.
peerpush_product_details is provided by the PeerPush MCP MCP server (peerpush/peerpush_mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.