[CodeLoop] You MUST call codeloop_verify after every code change. If .codeloop/config.json is missing, call codeloop_init_project FIRST. Initialize CodeLoop in a project that hasn't been set up yet. Creates `.codeloop/config.json`, agent rules, MCP config, `artifacts/`, and `.gitignore` entries....
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 use codeloop_init_project to create or modify resources in Codeloop. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call codeloop_init_project repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Codeloop.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
codeloop_init_project:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Codeloop policy for all 29 tools.
Agents calling write-class tools like codeloop_init_project have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
[CodeLoop] You MUST call codeloop_verify after every code change. If .codeloop/config.json is missing, call codeloop_init_project FIRST. Initialize CodeLoop in a project that hasn't been set up yet. Creates `.codeloop/config.json`, agent rules, MCP config, `artifacts/`, and `.gitignore` entries. Call this: - ALWAYS as your FIRST CodeLoop tool call in any new workspace where `.codeloop/config.json` does not yet exist (no exceptions). - Whenever a CodeLoop tool response begins with the "[CodeLoop] This project has not been initialized" hint. This is the mandatory bootstrap step — without it, the rest of the loop (verify → diagnose → gate_check) has no config to read and no rules to apply. The bootstrap is fast (<1s), idempotent, and only runs once per project. After it completes, proceed directly with `codeloop_verify`.. It is categorised as a Write tool in the Codeloop MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for codeloop_init_project. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Codeloop MCP server.
codeloop_init_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the codeloop_init_project 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_init_project. 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_init_project 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.