Schema | mcp-agent-collaboration

mcp-agent-collaboration

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_AGENT_COLLAB_LOG`	No	Log file path for the agent collaboration server	/tmp/mcp-agent-collaboration.log
`MCP_AGENT_COLLAB_HOST`	No	Host address for the agent collaboration server	127.0.0.1
`MCP_AGENT_COLLAB_PATH`	No	Path for the MCP endpoint	/mcp
`MCP_AGENT_COLLAB_PORT`	No	Port for the agent collaboration server	8000

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 }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
create_topicB	Create a collaboration topic by name.
join_topicC	Join a topic with a friendly agent name and receive a join_token.
leave_topicC	Leave the joined topic.
send_messageB	Send a direct or broadcast message in the joined topic.
read_messagesA	Long-poll, read, and consume pending messages for the joined agent.
check_inC	Optionally send a message, then read pending messages in one tool call.
list_topicsA	List topics with member counts and pending in-memory message counts.
list_topic_membersB	List active members in a topic.

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/vkolotov/mcp-agent-collaboration'

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