Skill Detail
Expose Haystack pipelines as webhook endpoints with Hayhooks
Turn an existing Haystack pipeline into an HTTP or MCP endpoint without building and maintaining a custom wrapper service.
Integrations & ConnectorsMulti-Framework
Integrations & Connectors
Multi-Framework
Security Reviewed
⭐ 138 GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill expose-haystack-pipelines-as-webhook-endpoints-with-hayhooks
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
Python environment, Haystack pipeline definitions, hayhooks package, network access for HTTP serving, optional MCP clients
Install & setup
Install hayhooks in a Python environment, prepare the pipeline wrapper and pipeline definition files described upstream, then run the Hayhooks server and deploy the target pipeline as an endpoint.
Author
deepset
Publisher
Organization
Last updated
Apr 15, 2026
Quick brief
Use Hayhooks when an agent already has a Haystack pipeline and needs to serve it through HTTP, webhook-style, OpenAI-compatible, or MCP endpoints for other systems to call. The user is not invoking a generic AI platform here. The workflow is narrow: wrap a pipeline, deploy it, and expose a documented endpoint surface for handoffs. That scope boundary, serving existing Haystack pipelines as callable endpoints, keeps it distinct from a plain library or framework listing.