deepset · Data & retrieval
Haystack
Combine retrieval pipelines, language models, and tool-using agents in AI applications.
- Languages
- Python
- API surface
- Python pipelines and agents
- MCP capability
- MCP integration
APIs & SDKs
Compose components into pipelines or use a tool-calling agent. Haystack’s agent API connects a chat generator, tools and execution state.
Explore the developer documentation ↗Integrations
Retrieval components and model generators combine with application tools. Pipelines let you explicitly organize how data moves between components.
View framework integration resources ↗MCP integration
MCP support
The MCPToolset integration loads tools from a server for an agent or pipeline. Haystack documents stdio and Streamable HTTP, with SSE marked deprecated in the guide.
Evidence scope: Python haystack-integrations package. Documentation reviewed; runtime compatibility has not been tested.
Sources & review
Integration notes reviewed . Check the linked documentation for current package versions, language support and authentication requirements.
How we review directory entries →Related frameworks
Explore frameworks in the same category or from the same maintainer.
LlamaIndex