- Conduid
- Marketplace
- #replay
MCP servers tagged replay
21 live MCP servers tagged "replay", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with replay.
AegisTrace
Verifiable execution for durable AI agents: policy-bound workflow compiler, hash-chained journal, offline replay, and Merkle + Ed25519 proofs. Go.
Kitaru
Durable execution for AI agents, built on ZenML
Threads
Agents you can inspect, replay and trust. An agent framework for TypeScript and Python, built on an append-only event log.
Tape
Stdio proxy for MCP servers that logs all JSON-RPC traffic to a replayable trace file.
Mcprelay
The reliability layer for MCP tool calls — local-first policy, observability, and a dead-letter queue with replay for any stdio MCP server.
LLM Workbench
Model Context Protocol (MCP) server factory and HTTP handler that exposes an LLM Workbench runtime over MCP.
Mcprelay
The reliability layer for MCP tool calls — local-first policy, observability, and a dead-letter queue with replay for any stdio MCP server.
CLI
Observability dashboard for MCP servers — record, replay, and debug every tool call with latency tracking, error traces, usage analytics, and real-time diff comparisons.
Aevum
Open-source AI agent governance kernel — cryptographic audit trails, consent-checked data access, and verifiable decision records.
Agentbox
Black box footage for AI agents: local replay of terminal output, file diffs, MCP tool calls, and risk flags.
Agent Recorder
📊 Convert agent framework logs into a standard trajectory format for easy analysis and integration within data pipelines.
Loop Engineering Opentine
Loop engineering with verifiable provenance: every iteration of a branching agent loop becomes a recorded step in a content-addressed opentine artifact you can diff, fork, resume,…
Agentbox
Black box footage for AI agents: local replay of terminal output, file diffs, MCP tool calls, and risk flags.
Agent Recorder
📊 Convert agent framework logs into a standard trajectory format for easy analysis and integration within data pipelines.
Terx
Browser-agent memory that turns repeated workflows into deterministic replays.
Agent Studio Open
Connect agent systems, inspect tool traces, replay failures, compare candidates, and export regression evidence.
Assay Protocol
MCP boundary spec and notary layer for verifiable Assay evidence.
Tracefact
Evidence-first reliability reports and reproducible replay for coding and browser agents.
Arcade Cabinets
The arcade: games made from what MCP servers said on the wire. Ghost on the Menu (a replay shooter) and Vibe Typer (a typing game where you are the coding agent), both playable on…
Tool Call Replay Harness
Offline replay and assertion harness for AI agent tool-call transcripts, fixtures, retries, budgets, JUnit reports, and CI gates.
Aetiory
Fork failed Python programs into tested alternate outcomes, with original-run controls and guarded replay.