agent-replay-debugger-mcp

Purpose: Debugging and auditing agentic AI workflows by enabling deterministic replay and step-level inspection.

Inferred · not functionally tested

Audience: AI developers and researchers working with agentic systems

Inferred · not functionally tested

Functions: monitoring

Inferred · not functionally tested

Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

agent-replay-debugger-mcp is a Debugging & profiling project. Inferred · not functionally tested: It focuses on debugging and auditing agentic AI workflows by enabling deterministic replay and step-level inspection. Inferred · not functionally tested: It is built as an open-source project for AI developers and researchers working with agentic systems. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the command line, and it can be self-hosted.

Behind agent-replay-debugger-mcp is MEOK AI Labs, and it first shipped in 2026. The project is developed in the open on GitHub with 18 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are step debugger, replay agent steps, and deterministic replay. Basis unknown · not verified: Catalogued interfaces include an MCP server.

Summary written by a language model from the project’s public pages.