
Threadline Mcp
Enables multi-agent coordination through a zero-config messaging relay. Agents can discover each other, send messages, and receive replies without manual setup. Built as part of the Instar coherence infrastructure, which focuses on durable memory, cross-session identity, and self-evolving agents. Think of it as a lightweight message bus for agent-to-agent communication, useful when you're running multiple Claude Code sessions or separate agent instances that need to coordinate tasks, share context, or hand off work. The relay handles discovery and routing so agents don't need hardcoded endpoints or shared databases to collaborate.
- tools
- 2
- transport
- STDIO
- env vars
- 3
- last updated
- Mar 10, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
injectInject user context into a base system prompt before an LLM call. Returns an enriched prompt with relevant facts about the user automatically inserted.3 params
Inject user context into a base system prompt before an LLM call. Returns an enriched prompt with relevant facts about the user automatically inserted.
apiKeystringbasePromptstringuserIdstringupdateUpdate a user's context after an LLM interaction. Extracts structured facts from the conversation and stores them for future sessions.4 params
Update a user's context after an LLM interaction. Extracts structured facts from the conversation and stores them for future sessions.
agentResponsestringapiKeystringuserIdstringuserMessagestringSponsors
Configuration
THREADLINE_RELAYCustom relay WebSocket URL (default: wss://threadline-relay.fly.dev/v1/connect)
THREADLINE_NAMEAgent display name (default: auto-generated from username and hostname)
THREADLINE_CAPSComma-separated agent capabilities for discovery (default: chat)
Readme
Details
- Repository
- github.com/sagemindai/instar
- Categories
- AI & LLM Tools, Communication & Messaging
- Package
threadline-mcp- Transport
- STDIO
- Registry
- MCP registry, active