[CodeLoop] You MUST call codeloop_verify after every code change. If .codeloop/config.json is missing, call codeloop_init_project FIRST. Analyze a recorded video of a user interaction flow to verify it completes as expected. Use this tool when: - You have recorded yourself interacting with ALL e...
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_interaction_replay 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_interaction_replay 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_interaction_replay:
rules:
- action: allowSee the full Codeloop policy for all 29 tools.
Agents calling read-class tools like codeloop_interaction_replay 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. Analyze a recorded video of a user interaction flow to verify it completes as expected. Use this tool when: - You have recorded yourself interacting with ALL elements of the app via codeloop_start_recording - You want to verify that every page loaded, every button worked, every form submitted - You need evidence-based assessment of a recorded flow against expected behavior IMPORTANT: The expected_flow parameter should describe EVERY interaction you performed during recording. Be specific — list each page visited, each button clicked, each form filled. Example: "Homepage loaded → clicked Work nav link → Work section scrolled into view → clicked CodeLoop card → opened codeloop.tech → navigated back → clicked Lifestyle nav link → scrolled to Lifestyle section → clicked Privacy link in footer → Privacy page loaded → clicked browser back → homepage restored" Key frames are extracted from the video and returned as images for you to analyze visually. If app logs were captured during the recording session, they are included alongside the frames so you can correlate visual state with runtime errors. Returns: extracted key frames as images + expected flow description + app logs for visual and runtime analysis.. 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_interaction_replay. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Codeloop MCP server.
codeloop_interaction_replay 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_interaction_replay 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_interaction_replay. 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_interaction_replay 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.