Detect conflicts between your local decisions and team members' decisions. Call this before committing to check for potential conflicts. The tool compares: 1. **Overlapping code**: Decisions affecting the same files 2. **Contradictory rationale**: Decisions with opposing reasoning 3. **Constrai...
Bulk/mass operation — affects multiple targets
Part of the Kawa Code MCP MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call detect_intent_conflicts to retrieve information from Kawa Code MCP 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 detect_intent_conflicts 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:
detect_intent_conflicts:
rules:
- action: allowSee the full Kawa Code MCP policy for all 17 tools.
Agents calling read-class tools like detect_intent_conflicts 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.
Detect conflicts between your local decisions and team members' decisions. Call this before committing to check for potential conflicts. The tool compares: 1. **Overlapping code**: Decisions affecting the same files 2. **Contradictory rationale**: Decisions with opposing reasoning 3. **Constraint mismatch**: Decisions applying different constraints Returns: - hasConflicts: Whether any conflicts were detected - hasCriticalConflicts: True if constraint mismatches found (high priority) - conflicts: List of conflict details with affected files and authors - overlappingFiles: All files affected by both local and team decisions Note: Team decisions must be provided (fetched from API).. It is categorised as a Read tool in the Kawa Code MCP MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for detect_intent_conflicts. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Kawa Code MCP MCP server.
detect_intent_conflicts 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 detect_intent_conflicts 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 detect_intent_conflicts. 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.
detect_intent_conflicts is provided by the Kawa Code MCP MCP server (@kawacode/mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept