AI agents use pr_claim_work to create or update resources in Pr Review — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pr Review environment.
Claiming a file partition is a reversible write-like operation that marks or reserves a unit of work for a specific reviewer/process. It does not delete data, execute code, or move money, but it does modify state (ownership/assignment of a partition) in a way that affects parallel processing coordination. Misuse could cause review tasks to be incorrectly assigned or blocked, hence medium severity.
From the tool's definition "Claim file partition for parallel PR review processing" — the tool claims/reserves a partition, which is a write/lock operation assigning work ownership.
Attacks that exploit this kind of access
Claim file partition for parallel PR review processing. It is categorised as a Write tool in the Pr Review MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pr Review MCP server in PolicyLayer and add a rule for pr_claim_work: 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 Pr Review. Nothing to install.
pr_claim_work 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 pr_claim_work 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 pr_claim_work. 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.
pr_claim_work is provided by the Pr Review MCP server (thebtf/pr-review-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 →