About basethread
BaseThread is a shared-context service for teams, letting different AI tools read relevant project context and write activity, decisions, and tasks to a shared graph. It is intended for teams using multiple AI tools to reduce repeated explanations and conflicting information.
Key features
- 01Shared team context graph
- 02Relevant context retrieval
- 03Writes activity, decisions, and tasks
- 04Hosted remote server with OAuth
- 05Install and security guides
Use cases
- 01Share project context across a team's AI tools
- 02Retain work activity and decisions between sessions
- 03Reduce repeated project explanations
- 04Keep project answers consistent across tools
MCP support
BaseThread provides shared context through a hosted Streamable HTTP remote MCP server. MCP clients can read context and write work information; connections use OAuth.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.basethread.ai/mcpclaude mcp add --transport http ai-basethread-basethread https://mcp.basethread.ai/mcp{"mcpServers":{"ai-basethread-basethread":{"type":"http","url":"https://mcp.basethread.ai/mcp"}}}Open in Cursor{"servers":{"ai-basethread-basethread":{"type":"http","url":"https://mcp.basethread.ai/mcp"}}}Open in VS Code{"mcpServers":{"ai-basethread-basethread":{"type":"http","url":"https://mcp.basethread.ai/mcp"}}}{"mcpServers":{"ai-basethread-basethread":{"serverUrl":"https://mcp.basethread.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEBaseThread MCP
The public home for BaseThread's Model Context Protocol server , its registry manifest, install guide, and security page.
BaseThread is one shared context your whole team's AI tools read and write over MCP. Claude Code, Cursor, ChatGPT, Windsurf, and Copilot each read the relevant slice of a shared, company-structured context graph at the start of a session and write activity, decisions, and tasks back as work happens , so no one re-explains the project and answers stop contradicting. Free to start, no card.
Connect
The server is hosted (remote, streamable-HTTP + OAuth) , no local install needed:
claude mcp add --transport http basethread https://mcp.basethread.ai/mcp
Or add https://mcp.basethread.ai/mcp in any MCP client that supports remote servers. Full instructions
for every client, plus the tool list: llms-install.md.
In this repo
- server.json , the Official MCP Registry manifest (
ai.basethread/basethread). - llms-install.md , agent-readable install + configuration guide.
- Security & privacy , the canonical security page (access model, OAuth, tenancy). Mirrored in SECURITY.md.
- PUBLISHING.md , how the registry listing is published and republished.
Links
- Product: https://basethread.ai
- App: https://app.basethread.ai
- Live demo (no signup): https://app.basethread.ai/demo
- MCP endpoint: https://mcp.basethread.ai/mcp
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.