MCP server for Threadline — the memory governance layer for AI agents.
Use Threadline's persistent, user-consented memory in any MCP-compatible client: Cursor, Claude Desktop, or your own agent.
npm install -g threadline-mcpRelated MCP server: supermem
Get your API key at threadline.to/dashboard.
Add to claude_desktop_config.json:
{
"mcpServers": {
"threadline": {
"command": "threadline-mcp",
"env": {
"THREADLINE_API_KEY": "tl_live_your_key_here"
}
}
}
}Add to your MCP config in Cursor settings:
{
"threadline": {
"command": "threadline-mcp",
"env": {
"THREADLINE_API_KEY": "tl_live_your_key_here"
}
}
}THREADLINE_API_KEY=tl_live_your_key_here threadline-mcpinjectInject user context into a base system prompt before an LLM call.
{
"userId": "user-uuid",
"basePrompt": "You are a helpful assistant."
}Returns an enriched prompt with relevant facts about the user automatically inserted.
updateUpdate a user's context after an LLM interaction. Extracts and stores structured facts for future sessions.
{
"userId": "user-uuid",
"userMessage": "I prefer concise answers and I'm building in TypeScript.",
"agentResponse": "Got it, keeping it brief."
}Your MCP client (Cursor / Claude Desktop)
│
▼
threadline-mcp (this package)
│
▼
api.threadline.to
│
┌────┴────┐
▼ ▼
Supabase Redis
(context) (<50ms)inject() — fetches stored context, scores by recency + relevance, returns enriched prompt
update() — two-stage extraction pipeline classifies and stores new facts across 7 scopes
Docs: threadline.to/docs
Dashboard: threadline.to/dashboard
Support: vidur@threadline.to
Inject user context into a base system prompt before an LLM call. Returns an enriched prompt with relevant facts about the user inserted automatically.
Inputs: userId (required), basePrompt (required).
Update a user's context after an LLM interaction. Threadline extracts structured facts from the conversation and stores them for future sessions.
Inputs: userId (required), userMessage (required), agentResponse (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: 'inject' handles pre-LLM call context insertion, while 'update' handles post-interaction context extraction and storage. There is no overlap in functionality, making them easily distinguishable for an agent.
Both tools use simple, imperative verb names ('inject' and 'update') that are consistent in style and length. This follows a predictable pattern without any deviations or mixed conventions.
With only 2 tools, the server feels thin for its apparent purpose of managing user context across LLM interactions. A typical context management system might benefit from additional operations like retrieving or deleting context, making this set under-scoped.
The tools cover the core workflow of injecting and updating user context, but there are notable gaps. For example, there is no tool to retrieve stored context for review or delete outdated context, which could limit agent functionality in multi-session scenarios.
shared AI-context layer for teams — persistent memory your agents search and update over MCP
Hosted memory for AI agents over MCP. One memory shared by all your agents.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
An MCP memory server. One memory your agents share — across models, devices and apps.
