ToolReplay MCP Server
brandynfisher/ToolReplay
[](https://agentrank-ai.com/tool/brandynfisher--ToolReplay/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
brandynfisher/ToolReplay is a Python agent tool licensed under MIT. Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI. Topics: ai-agents, audit, cli, determinism, hash-chain, jsonl, permissions, python, replay, scope, security, tool-call.
Ranked #14860 out of 24846 indexed tools.
Ecosystem
Score Breakdown
184 stars → growing community
Last commit 1mo ago → moderate activity
0/1 issues closed → many open issues
9 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/brandynfisher--ToolReplay/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/brandynfisher--ToolReplay/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/brandynfisher--ToolReplay" alt="AgentRank"></a> Matched Queries
From the README
# ToolReplay ToolReplay audits a recorded transcript of an AI agent's tool calls and reports where the session was non-deterministic, redundant, or outside its declared permissions. Here is the tool working, right now, on the dirty sample that ships in this repository. The command is shown above its output, and the output is pasted verbatim from a run in this checkout: ``` $ python -m toolreplay replay samples/session-dirty.jsonl calls: 6 divergence: index 5 findings: 2 index 2: redundant-call: tool 'read_file' repeats the identical call at index 1 with no state change between them index 5: non-determinism: tool 'search' returned a different response than the identical call at index 3 exit code: 1 ``` ## What just happened Those three header lines and two findings are the whole audit of a six-call session. Read them top to bottom. `calls: 6` is the number of records parsed from `samples/session-dirty.jsonl`. Parsing is strict, so a six here means six wellRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.