Semurg agent memory
io.semurg/agent-memory ยท version 11.153.20261103
Community listing. Not installed or verified by cosmic-mcp. Read the source and its permissions before you run it.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
https://github.com/One-Semurg/semurg-mcpQuick facts
- Listing: Verified domain
- Published Nov 3, 21:30 UTC
- Transport: stdio
- Package: pypi
semurg0.1.6 - Listed by cosmic-mcp: Nov 8, 19:01 UTC
Details
- Repository: https://github.com/One-Semurg/semurg-mcp
- PyPI: https://pypi.org/project/semurg/
- Website: https://one.semurg.io/blog/semurg-agent-memory-over-mcp
- Needs settings:
SEMURG_URLSEMURG_API_TOKENSEMURG_SCOPE
Setup snippets
Generated from the registry entry. cosmic-mcp has not run or reviewed this server; values in angle brackets are yours to fill in.
Run it locally (pypi)
uvx 'semurg==0.1.6'Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"agent-memory": {
"args": [
"semurg==0.1.6"
],
"command": "uvx",
"env": {
"SEMURG_API_TOKEN": "<your semurg api token>",
"SEMURG_SCOPE": "<your semurg scope>",
"SEMURG_URL": "<your semurg url>"
}
}
}
}Claude Code
claude mcp add 'agent-memory' -- uvx 'semurg==0.1.6'Cursor (.cursor/mcp.json)
{
"mcpServers": {
"agent-memory": {
"args": [
"semurg==0.1.6"
],
"command": "uvx",
"env": {
"SEMURG_API_TOKEN": "<your semurg api token>",
"SEMURG_SCOPE": "<your semurg scope>",
"SEMURG_URL": "<your semurg url>"
}
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"agent-memory": {
"args": [
"semurg==0.1.6"
],
"command": "uvx",
"env": {
"SEMURG_API_TOKEN": "<your semurg api token>",
"SEMURG_SCOPE": "<your semurg scope>",
"SEMURG_URL": "<your semurg url>"
},
"type": "stdio"
}
}
}Related servers
- AgentPlaybooks Verified domain
Vendor-neutral home for portable agents: skills, MCP tools, memory, canvas, and secret proxy. - Achromat Machine Operational Memory Verified domain
Recall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool. - 0Latency Memory
Persistent memory layer for AI agents. Sub-100ms recall, semantic search, knowledge graphs. - 100Trades Verified domain
Read your 100Trades day-trading simulator record: trades, R, stops, notes and analytics. - 2Mind Verified domain
Personal AI memory: search and read your notes and todos; changes wait for your approval. - 6DuckLearn MCP Verified domain
Connect agents to 6DuckLearn memory, approvals, and runtime control.