Skip to main content
Glama

ipc

Enables AI agent sessions to exchange messages and coordinate actions over TCP connections for collaborative tasks.

Instructions

Inter-process communication between AI agent sessions over TCP. Use when the user wants to share information, coordinate, or collaborate with another AI agent session (e.g. "ask the other session about X", "send this to the game server session", "wait for a message"). Each call handles one message. For back-and-forth, alternate send and receive.

Operations: send: Connect to remote host and send a text message. receive: Listen on a port and block until a message arrives (or timeout). Auto-responds to PING with PONG. No tokens consumed while waiting. ping: Send PING to remote host, wait for PONG, measure RTT.

Conversation flow: Session A: receive(port=19900, timeout=120) -- blocks waiting Session B: send(host="<A's address>:19900", message="question or data...") Session A gets the message, processes it, then: Session A: send(host="<B's address>:19900", message="response...") Session B: receive(port=19900, timeout=120) -- gets the response

Same machine: host="localhost:19900". Different machines: use IP address. For local-only, set bind="127.0.0.1" on receive. Max message size: 1MB. Max timeout: 300s.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYesOperation: send, receive, ping,required
hostNoRemote host:port (e.g. '192.168.1.5:19900'). For send/ping
portNoPort to listen on. For receive. Default: 19900
messageNoMessage text to send. For send
timeoutNoTimeout in seconds. receive default: 60 (max 300), send/ping default: 10
bindNoBind address for receive. Default: 0.0.0.0 (all interfaces). Use 127.0.0.1 for local only

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/knewstimek/agent-tool'

If you have feedback or need assistance with the MCP directory API, please join our Discord server