MCP Server plugin
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Server pluginList captured runs and inspect the latest failed run, explaining its replay confidence."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AgentTape
Turn one failed Codex run into a portable regression test.
AgentTape is an open-source, local-first Codex plugin that records supported tool failures as redacted, versioned .tape evidence. Inspect what failed, fork the captured run at a controlled boundary, and save the result as an offline regression test that can run in CI without another model call.
Most trace tools help you observe a failure. AgentTape is built to turn that failure into a small, reviewable artifact that prevents the same bug from returning.
Codex tool failure
↓
redacted .tape evidence
↓
inspect → inject one condition → compare branches
↓
save assertions → run offline in CIWhy AgentTape
Failure artifact, not another dashboard. A
.tapeis portable evidence you can inspect, review, share, and commit with a bug fix.Codex-native capture. Bundled hooks cover the 11 current Codex lifecycle, prompt, compaction, subagent, permission, and local tool events after the user reviews and trusts them—no application instrumentation required.
Local and privacy-conscious. Runtime captures stay inside the active project, common secret-bearing fields are recursively redacted, and committed regressions retain only event/tool structure rather than raw tool inputs or outputs.
Controlled failure injection. Fork recorded evidence with permission-denied, timeout, rate-limited, malformed-JSON, or truncated-response results.
Offline regression tests. Structural replay and assertions use captured evidence with zero model calls and zero live tool calls.
Honest replay confidence. AgentTape reports coverage and limitations instead of claiming every external system can be reproduced bit for bit.
Related MCP server: ResiliReplay
Install from GitHub
Prerequisites: Codex and Node.js 20 or newer.
codex plugin marketplace add jiangkoumo/agenttape
codex plugin add agenttape@agenttapeStart a new Codex task after installation and review the bundled hooks before trusting them. Captures are then stored under the active project's .agent-tape/ directory.
Two-minute workflow
First, use Codex normally until a supported local tool call fails. Then ask:
Use tool search to find AgentTape. List captured runs, inspect the latest
failed run, and explain the first recorded failure and replay confidence.AgentTape exposes four MCP tools:
Tool | Purpose |
| Find valid captures in the active workspace |
| Inspect events, failures, redaction, and replay confidence |
| Inject one supported failure condition at a recorded boundary |
| Save reviewed assertions under |
Run a saved regression locally or in CI:
node plugins/agenttape/dist/agenttape-cli.mjs test tests/agenttapePassing assertions exit with code 0. Validation or assertion failures exit nonzero, and captured comparison values are omitted from failure output.
The repository CI runs the same directory command through npm run test:tapes, so every reviewed .tape added under tests/agenttape/ becomes an offline regression automatically.
What a .tape captures
Raw Tape v1 captures keep the evidence needed for structural debugging; save_regression then produces a stricter portable subset:
Run identity, timestamps, source coverage, and explicit limitations.
Ordered lifecycle, permission, and supported local tool events.
Tool inputs, outputs, explicit failures, and the first failure boundary.
A redaction manifest that records where values were removed.
Optional fork metadata, injected conditions, and structural assertions.
Replay-confidence inputs so consumers can distinguish strong evidence from playback-only traces.
Saved regressions omit raw prompts, tool inputs/outputs, artifacts, local session/turn/use IDs, absolute paths, and nested tape inventory. Assertions that contain user-supplied expected values are rebuilt from the sanitized injected result or replaced with safe defaults.
The tape schema is independent from the UI and recorder implementation. See Tape Schema v1.
Regression assertions
AgentTape currently supports deterministic checks for:
A field equals an expected value.
A tool is present or absent.
Tool execution order matches expectations.
Retry count stays below a maximum.
The final run status matches the expected status.
Replay confidence meets a minimum threshold.
Reviewed regression artifacts are written under tests/agenttape/ and are not overwritten by default.
Replay boundaries
AgentTape currently provides structural replay, not full agent re-execution. It reuses captured state, substitutes one recorded tool result, and stops at the injected boundary. It does not regenerate downstream model reasoning.
Hosted tools, uncaptured external state, and changes in third-party systems may be absent. A redaction marker proves that AgentTape's redactor ran; it cannot prove arbitrary free-form text contains no secret. Review every .tape before sharing it.
See Privacy and Security for the complete trust boundary.
Repository layout
plugins/agenttape/
.codex-plugin/plugin.json # Codex plugin manifest
hooks/hooks.json # Recorder lifecycle hooks
skills/capture-failure/ # Guided capture workflow
dist/mcp-server.mjs # Self-contained bundled MCP server
scripts/ # Recorder, schema, and assertion CLI
schemas/ # Versioned .tape schemaThe repository also contains an optional Branch Canvas prototype under src/ and an experimental stateless HTTP MCP under remote/. They exercise the same tape and replay concepts but are not required to install or use the Codex plugin.
Local development
git clone https://github.com/jiangkoumo/agenttape.git
cd agenttape
npm ci
npm run test:plugin-release
npm run build:plugin
codex plugin marketplace add .
codex plugin add agenttape@agenttapeThe committed plugins/agenttape/dist/mcp-server.mjs allows marketplace installs to run without building the repository. Rebuild and commit it whenever MCP source changes.
Run npm test and npm run build when changing the optional Branch Canvas, Sites adapter, or remote HTTP MCP surfaces.
Mutual AgentTape × ToolFence development follows the mirrored alignment contract. The five first-round real Codex scenarios are specified in the AgentTape-side execution guide.
Uninstall
codex plugin remove agenttape@agenttape
codex plugin marketplace remove agenttapeContributing
Issues and pull requests are welcome. See Contributing, Code of Conduct, and Changelog.
License
MIT. See LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Runtime permission, approval, and audit layer for AI agent tool execution.
Agent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
A witness layer for AI agent tool calls.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables step-debugging, deterministic replay, and signed audit evidence for AI agents, compliant with EU AI Act.MIT
- AlicenseNot gradedqualityBmaintenanceLocal-first MCP and coding-agent reliability harness that captures bounded, sanitized failure evidence and generates deterministic executable regression tests. Capture is opt-in; no API key or hosted service is required.2Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables one coding agent to inspect, configure, debug, and repair another agent over stdio MCP, with redacted reads and confirm-gated writes and restarts.MIT
- AlicenseNot gradedqualityCmaintenanceEnables evidence-first regression testing for AI agents by turning production traces into reviewed, replayable cases that gate releases. It supports reproducible, auditable agent evaluation with controlled tool execution, evidence-based judging, and versioned quality gates.MIT