sqry is a semantic code search tool that parses source code into an AST and builds a graph of symbols and relationships, allowing users to search by code structure rather than text.
From the registry: AST-based semantic code search: 33 tools, 35 languages, call tracing, impact analysis
$ curl -fsSL https://raw.githubusercontent.com/verivus-oss/sqry/main/scripts/install.sh | bash -s -- --component allhttps://sqry.devPlease install the `sqry-verivusoss` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **sqry-mcp binary** — Install sqry-mcp via installer script or build from source (Rust 1.94+). Run sqry index in codebase first. Run: `curl -fsSL https://raw.githubusercontent.com/verivus-oss/sqry/main/scripts/install.sh | bash -s -- --component all` (https://sqry.dev)
Canonical MCP server config (stdio transport):
- command: `sqry-mcp`
- args: []
- optional environment variables:
- `SQRY_CACHE_ROOT`: Custom cache location (example: `/mnt/ssd/.sqry-cache`)
- `SQRY_CACHE_MAX_BYTES`: Cache size limit in bytes (example: `524288000`)
Note: Same as sqry — semantic code search MCP with 34 tools for AST-based code graph analysis. Requires sqry-mcp binary installed and sqry index run first. Both slugs point to the same repo (verivus-oss/sqry).
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MCP server for searching Airweave collections with natural language queries.