Home › Knowledge & Memory › Umtri
Umtri
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Topics: Knowledge & Memory
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Remote (streamable-http)
https://mcp.umtri.io
Claude Code:
claude mcp add --transport http umtri-mcp https://mcp.umtri.io
Or add to your MCP client config:
{
"mcpServers": {
"umtri-mcp": {
"url": "https://mcp.umtri.io"
}
}
}
Package (npm 1.7.1)
npx -y [email protected]
Or add to your MCP client config:
{
"mcpServers": {
"umtri-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"UMTRI_API_TOKEN": "<YOUR_VALUE>"
}
}
}
}
UMTRI_API_TOKENrequired secret — Personal access token from app.umtri.io → Settings → API Tokens. Read tokens cannot call write tools.UMTRI_API_BASE— Override the API base URL. Defaults to https://api.umtri.io — set only when self-hosting.
Related servers
modelcontextprotocol/servers
Direct local file system access.
Context7
Up-to-date docs for AI agents
hindsight
Hindsight: long-term memory for AI agents modeled on human memory.
cognee
Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.
Skill_Seekers
Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, exportable to vector…
basic-memory
Local-first knowledge management with bi-directional LLM sync via Markdown files.
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry