Save the current project and/or todolist as context so other tools can be called without explicit IDs. Also accepts an optional stageOrder (comma-separated stage names) to override the inferred board order.
AI agents use set_context to create or update resources in Proofhub — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Proofhub environment.
This tool modifies stored context state that affects the behavior of other tools on the server. While not destructive (the changes are reversible) and not as severe as executing arbitrary code, it performs a state-changing write operation.
From the tool's definition The tool 'set_context' saves/modifies state ('Save the current project and/or todolist as context') which persists for subsequent tool calls. This is a write operation that creates or modifies contextual data.
Attacks that exploit this kind of access
Save the current project and/or todolist as context so other tools can be called without explicit IDs. Also accepts an optional stageOrder (comma-separated stage names) to override the inferred board order. It is categorised as a Write tool in the Proofhub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Proofhub MCP server in PolicyLayer and add a rule for set_context: 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 Proofhub. Nothing to install.
set_context 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 set_context 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 set_context. 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.
set_context is provided by the Proofhub MCP server (yashmody/proofhub-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 →