Skip to contentakb MCP Server — Install for Claude, Cursor & VS Code | MCPpediaAakb MCP Server
Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.
13LimitedInstall
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"dnotitia-akb": {
"command": "npx",
"args": [
"-y",
"akb-mcp@2.0.4"
],
"env": {
"AKB_MCP_URL": "",
"AKB_PAT": "YOUR_AKB_PAT"
}
}
}
}
Related servers
FMCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.
Environment
| Name | Required | Notes |
|---|
| AKB_MCP_URL | Yes | Your AKB backend MCP endpoint, e.g. https://akb.example.com/mcp/ — or try the public demo at https://akb-demo.agent.seahorse.dnotitia.ai/mcp/ |
| AKB_PAT | Yes | AKB Personal Access Token (akb_...). Create one in your AKB instance, or sign up on the public demo with any email to get one. Secret. |
Tools show up when the registry metadata or the repository README lists them. GitHub enrichment fills this in when a token is configured.
About
Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.
FAQ
- What is akb?
- Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.
- How do I install akb?
- Pick a client above and copy the generated config. Cursor and VS Code also have a deep link when the server can run locally or remotely.
- Is akb official?
- No. Registry-listed is not the same as vendor-official. Read the methodology for the difference.
- How is the trust score calculated?
- This listing scores 13 (Limited). The formula is published on the methodology page.
Reviews
0 published · no average
Sign in to review this server.
Good
Search, read, annotate, and add to your Zotero research library, local or web.
HLocal-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
HTells an agent what changed on a server since it last looked - status, Docker, backups, Proxmox.
KRead-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.
MLocal-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.