Close a forward-intent page. Sets frontmatter.status=
AI agents use intent_resolve to create or update resources in DevFlow MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DevFlow MCP Server environment.
The tool creates or modifies document state by changing a frontmatter status field. This is a Write operation because it updates data reversibly—the status can be changed again or reverted. It is not Execute (which would trigger external operations or run code) nor Destructive (the action is not irreversible).
From the tool's definition Tool description indicates it 'Close[s] a forward-intent page' and 'Sets frontmatter.status='. This modifies data (the status field in a document's frontmatter) in a reversible manner.
Attacks that exploit this kind of access
Close a forward-intent page. Sets frontmatter.status=. It is categorised as a Write tool in the DevFlow MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DevFlow MCP Server MCP server in PolicyLayer and add a rule for intent_resolve: 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 DevFlow MCP Server. Nothing to install.
intent_resolve 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 intent_resolve 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 intent_resolve. 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.
intent_resolve is provided by the DevFlow MCP Server MCP server (klausfreiberufler/devflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →