Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
web-agent-protocol
MCP servers🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
git clone https://github.com/OTA-Tech-AI/web-agent-protocol.git -
agent-replay
MCP serversRecord and replay AI agent execution for debugging
agent-replay-mcp@0.1.1 -
Session Replay
MCP serversRead and triage bug reports captured by Session Replay for your verified domains.
-
agent-replay-debugger-mcp
MCP serversAgent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for
agent-replay-debugger-mcp@1.0.7 -
Sequential session replay
MCP serversSession replay and product analytics. Read cases, sessions, verdicts and funnels.
-
AgentFirstStack Replay
MCP serversSession replay as readable transcripts: rage and dead clicks, JS errors, heatmaps. Open source.
-
Replai
MCP serversSet up, test and publish an AI customer support Agent for your SaaS product.
-
Span-level replay: fork from the failure
MCP serversFork-replay one recorded span from a failed agent run and get an attribution verdict.
-
claude-replay
MCP serversSession checkpoint & recovery for Claude Code: resume, search, tag, and export recorded sessions.
claude-replay@0.4.3 -
betterlytics
MCP serversOpen-source web analytics with session replay, error tracking, Core Web Vitals and uptime monitoring in one tool. Cookieless, EU-hosted cloud or self-hosted.
git clone https://github.com/betterlytics/betterlytics.git -
iPhone Use
MCP serversDrive a real iPhone from a Mac: read the screen as text, tap, type, scroll, replay saved flows.
-
statecli
MCP serversState replay and self-debugging for AI agents. Track, replay, undo, checkpoint.
statecli-mcp-server@0.5.0 -
ntfy-mcp-server
MCP serversSend, manage, and replay ntfy push notifications via MCP.
ntfy-mcp-server@2.4.1 -
Agent evidence
MCP serversOffline, read-only tools that verify AI claims against evidence and replay conformance vectors.
agent-evidence-mcp@0.2.6 -
nudge
MCP serversA typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.
git clone https://github.com/NekomyaDev/nudge.git -
orcareplay
MCP serversRead, replay and fork recorded coding-agent runs.
orcareplay@0.5.0 -
AgentWatch
MCP serversMulti-agent observability: cascade failure detection, heartbeats, and forensic replay
@nicofains1/agentwatch@0.3.1 -
BugProof
MCP serversCapture, replay, and debug failures with portable, executable bug artifacts
bugproof@1.6.5 -
pentest-ai
MCP serversOpen-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.
git clone https://github.com/0xSteph/pentest-ai.git -
Talaria
MCP serversErrors, traces, replays and logs from Talaria for coding agents.
-
Deptho
MCP serversReplay a crypto backtest's orders against trades and write tearsheets, locally.
deptho-mcp@0.1.0 -
agentao
MCP serversLocal-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.
git clone https://github.com/jin-bo/agentao.git -
EdgeDepth Research
MCP serversTest crypto-perpetual claims using recorded counts, baselines, and replay.
@edgedepth/research-mcp@0.11.0 -
Hesper Atlas Evidence
MCP serversVerify stock signals, replay evidence, provenance, freshness, and caveats.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.