cond_subscribe
AI agents invoke cond_subscribe to trigger actions in TermPipe MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The server context is high-risk (direct terminal access, REPL sessions, command execution). The 'cond_' prefix appears on sibling tools related to clipboard, hotkeys, and daemon operations, suggesting this tool interacts with a persistent terminal/REPL session. 'Subscribe' likely registers for events or messages from a session.
From the tool's definition Tool name 'cond_subscribe' on a server that provides 'direct terminal access to execute commands, manage files, and run persistent REPL sessions'. The tool description is empty and uninformative.
Attacks that exploit this kind of access
cond_subscribe. It is categorised as a Execute tool in the TermPipe MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TermPipe MCP server in PolicyLayer and add a rule for cond_subscribe: 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 TermPipe MCP. Nothing to install.
cond_subscribe is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cond_subscribe 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 cond_subscribe. 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.
cond_subscribe is provided by the TermPipe MCP server (wbind-core/termpipe-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 →