Pipelex MCP
Runs declarative Pipelex AI workflows (pipelines) as callable tools from an agent.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Pipelex MCP, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
Pipelex's MCP server exposes user-defined declarative pipelines so an agent can invoke a whole multi-step LLM workflow as a single tool call. Security surface: pipelines can chain external model and API calls with their own credentials, so a called pipeline is an opaque delegation the calling agent trusts.
Key features
- Expose declarative pipelines as MCP tools
- Chain multi-step LLM/data workflows
- Reusable, versioned pipeline definitions
Use cases
- Package a complex workflow as one agent tool
- Standardize repeatable AI processing steps