Skip to content

VectorSmith

Your vector database, forged into tools an agent can actually use.

Write a tools.yaml. VectorSmith compiles it into typed, tenant-guarded tools — then you either import them in Python or serve them over MCP.

pip install "vectorsmith[qdrant]"

Get started tools.yaml reference


Two doors, one YAML

You are building… Use
A Python agent (LangChain, LangGraph, OpenAI Agents, Anthropic SDK) load_tools / connect
A chat / IDE host (Claude Desktop, Claude Code, Codex, Cursor) vectorsmith serve as MCP

Same file either way. The agent never sees the store URL, the API key, or hidden tenant filters.


Find a page

Tutorials

Getting started Install, write YAML, prove a tool works
Claude Desktop Connectors, sandbox, --watch
HTTP / claude.ai serve --http, OAuth, /mcp

How-to

Use in an agent load_tools vs serve
Integrations Claude, Codex, Cursor, LangChain, LangGraph, Agents SDK, Anthropic
Next to other MCP servers Slack, GitHub, filesystem, vendor MCP
Deploy templates Docker, Kubernetes, Cloud Run, Fly

Reference

Vector stores Qdrant, pgvector, Chroma, Pinecone, Weaviate, Milvus
tools.yaml Every field, operators, pipelines, VBxxxx
CLI init · validate · serve · test · introspect · drafts · approve · auth
Python API connect, load_tools, extras, return envelope

Explanation

How it is put together Compile pipeline, two doors, what stays private
FAQ Desktop disconnects, env interpolation, HTTP auth, hybrids
Repository map What each top-level path is for

Examples in the repo: invoice + ticket YAML, agent apps, MCP host configs.


Install extras

pip install "vectorsmith[qdrant]"              # CLI + connect()
pip install "vectorsmith[qdrant,langchain]"    # + load_tools for LangChain / LangGraph
pip install "vectorsmith[qdrant,langgraph]"
pip install "vectorsmith[qdrant,openai-agents]"
pip install "vectorsmith[qdrant,anthropic]"

Store extras: see vector stores (qdrant · pgvector · chroma · pinecone · weaviate · milvus).


Status

0.1.0. Read-only tools from YAML. Application code uses from vectorsmith import load_tools or connect — do not import Engine.

Source: github.com/kjgpta/vectorsmith.