[CodeLoop] You MUST call codeloop_verify after every code change. If .codeloop/config.json is missing, call codeloop_init_project FIRST. Context-aware recommendation router. Use this tool when: - The user mentions a need (hosting, email, auth, analytics, etc.) but does not specify a category - Y...
Part of the Codeloop MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call codeloop_recommend_action to retrieve information from Codeloop 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 codeloop_recommend_action 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:
codeloop_recommend_action:
rules:
- action: allowSee the full Codeloop policy for all 29 tools.
Agents calling read-class tools like codeloop_recommend_action 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.
[CodeLoop] You MUST call codeloop_verify after every code change. If .codeloop/config.json is missing, call codeloop_init_project FIRST. Context-aware recommendation router. Use this tool when: - The user mentions a need (hosting, email, auth, analytics, etc.) but does not specify a category - You want automatic tool recommendations based on the project context and user intent - You prefer a single entry point rather than choosing between recommend_tool categories manually Returns: inferred category and budget, ranked recommendations, and routing explanation.. It is categorised as a Read tool in the Codeloop MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for codeloop_recommend_action. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Codeloop MCP server.
codeloop_recommend_action 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 codeloop_recommend_action 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 codeloop_recommend_action. 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.
codeloop_recommend_action is provided by the Codeloop MCP server (codeloop-mcp-server). 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.