Openexp
🔴DangerousQ-learning memory for Claude Code. Persistent memory that learns which context helps you get work done. Memories that lead to productive sessions (commits, PRs, tests) earn higher retrieval rank automatically. 16 MCP tools, hybrid BM25 + vector + Q-value scoring, local-first with Qdrant + FastEmbed.
Understand what it does
Tell your agent things like:
What this capability can access
This capability requires the following permissions:
This capability has elevated permissions including Execute Code. Review the permissions below carefully before granting access to your agent.
Set it up
Available on 1 platform. Pick yours:
Add to your MCP client configuration:
{
"mcpServers": {
"openexp": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-openexp"]
}
}
}Add to your README
Show that your tool is listed on AgentSift
[](https://agentsift.com/capabilities/openexp)Options: ?style=flat-square for square corners, ?score=false for simple “listed” badge
Related capabilities
Bedrock Kb Retrieval
Query Amazon Bedrock Knowledge Bases using natural language to retrieve relevant information from your data sources.
Aws Kb
Retrieve information from an AWS Knowledge Base using the Bedrock Agent Runtime.
Everything
Reference / test server with prompts, resources, and tools
Google Scholar Mcp Server
Search and access academic papers on Google Scholar.
Academia Mcp
Search for scientific publications across ArXiv, ACL Anthology, HuggingFace Datasets, and Semantic Scholar.
Academic Search
Search and retrieve academic paper information from multiple sources like Semantic Scholar and CrossRef.