pull_discussions
AI agents call pull_discussions to retrieve information from Phenomenai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Pull_discussions most likely retrieves discussion threads or comments associated with terms in the phenomenology glossary. This is a read operation with no apparent side effects or destructive capability. The lack of description lowers confidence slightly, but the naming pattern and server context strongly suggest data retrieval rather than modification or execution.
From the tool's definition Tool name 'pull_discussions' suggests retrieving discussion data. No description provided, but the server context indicates it's part of a glossary with 'community discussions' feature.
Attacks that exploit this kind of access
pull_discussions. It is categorised as a Read tool in the Phenomenai MCP Server, which means it retrieves data without modifying state.
Register the Phenomenai MCP server in PolicyLayer and add a rule for pull_discussions: 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 Phenomenai. Nothing to install.
pull_discussions 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 pull_discussions 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 pull_discussions. 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.
pull_discussions is provided by the Phenomenai MCP server (phenomenai-org/ai-dictionary-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 →