Schema | MCP Talk

MCP Talk

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_TALK_QUEUE`	No	Message queue directory	~/.mcp_talk/q/
`MCP_TALK_AUTO_CLEAN_HOURS`	No	Auto-delete messages older than N hours (0 to disable)	24
`MCP_TALK_MAX_MESSAGE_CHARS`	No	Maximum message length	2000

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
sendC	Send a message to another agent. Usage: send(to='claude', message='Hello!', namespace='myproject')
chkC	Check messages for an agent (shortcut). Usage: chk(agent='claude', namespace='myproject')
checkC	Check messages for an agent. Usage: check(agent='claude', namespace='myproject')
ackB	Acknowledge/delete a message after processing. Usage: ack(id='msg_id', namespace='myproject')
broadcastC	Send a message to all agents. Usage: broadcast(message='Team update', namespace='myproject')
listC	List all pending messages in the queue (PM visibility). Usage: list(namespace='myproject')
cleanC	Clean up old messages. Usage: clean(hours=24, namespace='myproject')
replyB	Reply to a message (acks original and sends response to sender). Usage: reply(id='msg_id', message='Got it!', namespace='myproject')

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/devinvenable/mcp-talk'

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