$ loading_
Search local markdown vector stores with LLMs and evaluate retrieval quality.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-ai-workspace" yet — see the docs or source repo.
Use mcp-ai-workspace to search the local Markdown vector store for "how to configure authentication for an MCP service", return the 5 most relevant results, and include brief summaries.
Relevant document snippets, source information, and short summaries to help locate the answer quickly.
Run the retrieval evaluation in mcp-ai-workspace for this query set, calculate hit rate and MRR, and identify which queries have poor recall.
Hit rate, MRR, per-query performance, and a list of retrieval issues that need optimization.
Use mcp-ai-workspace to search for "vector index update workflow". If the results are poor, analyze whether the issue is missing documents, chunking, or embedding-retrieval mismatch.
An assessment of result quality plus likely causes and recommendations for improvement.
Expose local Markdown knowledge to AI tools through MCP securely.
Chat with AI to retrieve documents and trigger MCP-powered tools.
Search local Markdown files and return full document contents for use.
Ground AI answers in local documents with search, summaries, and cited responses.
Search local documents to ground LLM answers in your files.
Turn unstructured documents into a searchable knowledge base for AI agents.