promptthrift_pin_facts
AI agents use promptthrift_pin_facts to create or update resources in PromptThrift MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PromptThrift MCP environment.
This tool creates or modifies stored facts within the conversation context management system. While it does not delete data (ruling out Destructive) or execute arbitrary code (Execute), it does persistently write configuration state that affects subsequent operations. The description is empty, reducing confidence slightly.
From the tool's definition Tool name 'promptthrift_pin_facts' indicates it modifies state by pinning/storing facts. The server description mentions 'pinned facts for preserving critical context,' confirming this tool writes data to preserve information.
Attacks that exploit this kind of access
promptthrift_pin_facts. It is categorised as a Write tool in the PromptThrift MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PromptThrift MCP server in PolicyLayer and add a rule for promptthrift_pin_facts: 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 PromptThrift MCP. Nothing to install.
promptthrift_pin_facts 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 promptthrift_pin_facts 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 promptthrift_pin_facts. 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.
promptthrift_pin_facts is provided by the PromptThrift MCP server (woling-dev/promptthrift-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 →