[CodeLoop] You MUST call codeloop_verify after every code change. If .codeloop/config.json is missing, call codeloop_init_project FIRST. Evaluate whether a section or feature meets all quality gates for completion. Use this tool when: - You believe a feature is complete and want evidence-based c...
Bulk/mass operation — affects multiple targets
Part of the Codeloop MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call codeloop_gate_check 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_gate_check 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_gate_check:
rules:
- action: allowSee the full Codeloop policy for all 29 tools.
Agents calling read-class tools like codeloop_gate_check 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. Evaluate whether a section or feature meets all quality gates for completion. Use this tool when: - You believe a feature is complete and want evidence-based confirmation - You need to check if all acceptance criteria are met before moving to the next section - You want a confidence score to decide whether to continue fixing or stop For UI projects: do NOT call this without BOTH screenshot AND video evidence. After this returns "ready_for_review", you MUST call codeloop_generate_dev_report to produce the development log before declaring the task complete. FIRST-USE BOOTSTRAP: If `.codeloop/config.json` does not yet exist in this workspace, call `codeloop_init_project` BEFORE calling this tool. The init hint prefix on every response in an uninitialized workspace is a hard instruction, not a suggestion. IMPORTANT: If this tool returns "continue_fixing", you MUST immediately loop back to codeloop_verify → codeloop_diagnose → fix → re-verify WITHOUT asking the user. This is an automatic quality loop. Do NOT stop and report partial progress. Only stop when this tool returns "ready_for_review" (confidence >= 94%) or "escalate". Maximum 15 loop iterations before escalation. Returns: pass/fail for each gate, overall confidence score, and recommendation.. 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_gate_check. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Codeloop MCP server.
codeloop_gate_check 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_gate_check 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_gate_check. 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_gate_check 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.