Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and other MCP clients.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add context-lens -- uvx context-lens~/.codex/config.toml
[mcp_servers.context-lens]
command = "uvx"
args = ["context-lens"]
# codex mcp add context-lens -- uvx context-lens~/.cursor/mcp.json
{
"mcpServers": {
"context-lens": {
"command": "uvx",
"args": [
"context-lens"
]
}
}
}.vscode/mcp.json
{
"servers": {
"context-lens": {
"type": "stdio",
"command": "uvx",
"args": [
"context-lens"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"context-lens": {
"command": "uvx",
"args": [
"context-lens"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"context-lens": {
"command": "uvx",
"args": [
"context-lens"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"context-lens": {
"command": "uvx",
"args": [
"context-lens"
]
}
}
}