Mark the active intent as completed and clear it. Call this after a successful git commit to: 1. Update the intent status (committed/pushed/done/abandoned) 2. Store the commit SHA for tracking 3. Clear the active intent so a new one can be started Status values: - "committed": Code is committed l...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Kawa Code MCP server.
Free to start. No card required.
AI agents use complete_intent to create or modify resources in Kawa Code MCP. 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 complete_intent repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Kawa Code MCP.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"complete_intent": {
"limits": [
{
"counter": "complete_intent_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Kawa Code MCP policy for all 21 tools.
These attack patterns abuse exactly the kind of access complete_intent gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Mark the active intent as completed and clear it. Call this after a successful git commit to: 1. Update the intent status (committed/pushed/done/abandoned) 2. Store the commit SHA for tracking 3. Clear the active intent so a new one can be started Status values: - "committed": Code is committed locally (default) - "pushed": Code has been pushed to remote - "done": Work is fully complete - "abandoned": Work was discarded without committing REQUIRED: Inspect the response after calling this tool. Four outcomes: 1. response.success === true: The task is complete. Briefly acknowledge the commit and — if response.committedDecisionCount > 0 — mention that N distilled architectural decisions were recorded for the intent. Do NOT enumerate the decisions inline; they're visible via the orchestration panel and via get_intent_decisions / get_relevant_context if the user wants details. If response.apiSyncDeferred === true, also mention that the API sync was deferred; the queued writes will replay on the next sync tick. 2. response.success === false AND response.conflicts is non-empty: The distillation produced decisions that contradict existing standards in this repo. Status stays "active" and NO decisions were written. Surface EACH conflict to the user with the proposed decision and the conflicting standard decision side-by-side. Then ask the user how to resolve. Common options to suggest: (A) Record a superseding decision via record_decision(type="fork", supersedes=["<existing-decision-id>"], rationale=...). Then retry complete_intent — the distiller may now find the new superseding decision in recall and the conflict resolves. (B) Abandon the intent: complete_intent(status="abandoned"). Decisions are soft-deleted but recoverable via activate_intent if the user changes their mind. (C) Keep the intent active and continue working. DO NOT silently retry — every retry runs the distiller (and the per-pair judge) again. Wait for the user's decision. 3. response.success === false AND response.reason === "transient-failure": The distiller LLM call or the conflict-check API call errored. The ephemerals are preserved (the bucket is intact), and the intent stays "active". Tell the user the failure stage (response.failedStage) and the underlying error, then suggest retrying once the issue clears, or abandoning if the failure persists. 4. In a non-interactive (autonomous) session: log the conflicts at WARN level and leave the intent active. A human review path exists via the panel.. It is categorised as a Write tool in the Kawa Code MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kawa Code MCP server in PolicyLayer and add a rule for complete_intent: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kawa Code MCP. Nothing to install.
complete_intent 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 complete_intent rule in your PolicyLayer 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 PolicyLayer policy for complete_intent. 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.
complete_intent is provided by the Kawa Code MCP server (kawacode-ai/kawa.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Kawa Code MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.