io.github.mdfifty50-boop/agent-replay
NPM · AGENT-REPLAY-MCP · SCANNED SEP 25
Record and replay AI agent execution for debugging
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 153 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability46
- 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 425 tokens (~47/item across 9 items; 8 tools + 1 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the io.github.mdfifty50-boop/agent-replay MCP server?
io.github.mdfifty50-boop/agent-replay runs locally as an npm package, launched with npx -y agent-replay-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · agent-replay-mcp
claude mcp add mdfifty50-boop-agent-replay -- npx -y agent-replay-mcp
{
"mcpServers": {
"mdfifty50-boop-agent-replay": {
"command": "npx",
"args": [
"-y",
"agent-replay-mcp"
]
}
}
} {
"servers": {
"mdfifty50-boop-agent-replay": {
"command": "npx",
"args": [
"-y",
"agent-replay-mcp"
]
}
}
} codex mcp add mdfifty50-boop-agent-replay -- npx -y agent-replay-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mdfifty50-boop-agent-replay": {
"type": "local",
"command": [
"npx",
"-y",
"agent-replay-mcp"
],
"enabled": true
}
}
} openclaw mcp add mdfifty50-boop-agent-replay --command npx --arg -y --arg agent-replay-mcp
mcp_servers:
mdfifty50-boop-agent-replay:
command: "npx"
args: ["-y", "agent-replay-mcp"] {
"McpServers": {
"mdfifty50-boop-agent-replay": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"agent-replay-mcp"
]
}
}
} assistant mcp add mdfifty50-boop-agent-replay -t stdio -c npx -a -y agent-replay-mcp
{
"mcpServers": {
"mdfifty50-boop-agent-replay": {
"command": "npx",
"args": [
"-y",
"agent-replay-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 −3
- Security disclosure: fail → unverified ▼ functional
- Stability: pass → 0.80 functional
- 23 Sept 26 +1
- Stability: 0.97 → pass security
- 21 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −4
- Security disclosure: unverified → fail ▼ functional
- Stability: pass → 0.77 functional
- 15 Sept 26 +1
- Stability: 0.97 → pass security
- Security disclosure: fail → unverified ▼ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 25 Sept 2026 · Analysed npm/agent-replay-mcp@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
compare_sessions ~57
Behavioral diff between two sessions. Aligns by step, highlights differences in types, inputs, outputs, and timing.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id_1 | string | yes | First session ID |
| session_id_2 | string | yes | Second session ID |
No output schema declared.
No examples provided.
export_session ~46
Export session as JSON or markdown transcript for sharing and offline analysis.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Export format: json or markdown |
| session_id | string | yes | Session ID to export |
No output schema declared.
No examples provided.
find_divergence_point ~60
Find where an agent first deviated from expected output. Accepts per-step array or single expected value.
| Name | Type | Req | Description |
|---|---|---|---|
| expected_output | – | – | Expected final output or per-step array of expected outputs |
| session_id | string | yes | Session ID to analyze |
No output schema declared.
No examples provided.
health_check ~20
Returns server health, uptime, version, and call stats
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
log_action ~105
Log a single action during a recording session. Captures input, output, reasoning, and timing.
| Name | Type | Req | Description |
|---|---|---|---|
| action_type | string | yes | Type of action (tool_call, llm_response, decision, error) |
| duration_ms | number | – | Duration in milliseconds |
| input | – | – | Input to the action |
| output | – | – | Output from the action |
| reasoning | string | – | Agent reasoning for this step |
| session_id | string | yes | Session ID returned by record_session |
No output schema declared.
No examples provided.
record_session ~57
Start recording all actions for an agent session. Returns a session_id to use with log_action.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Unique identifier for the agent being recorded |
| metadata | object | – | Optional metadata (task, model, environment) |
No output schema declared.
No examples provided.
replay_session ~37
Replay a recorded session step by step with full action detail, timing, and reasoning.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | Session ID to replay |
No output schema declared.
No examples provided.
stop_recording ~39
Stop recording and return session summary with action count, duration, and type breakdown.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | Session ID returned by record_session |
No output schema declared.
No examples provided.
What is the io.github.mdfifty50-boop/agent-replay MCP server?
io.github.mdfifty50-boop/agent-replay is an MCP server listed in the public MCP registry as io.github.mdfifty50-boop/agent-replay. Record and replay AI agent execution for debugging. This page covers its npm package (agent-replay-mcp).
Is the io.github.mdfifty50-boop/agent-replay MCP server safe to use?
io.github.mdfifty50-boop/agent-replay scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.mdfifty50-boop/agent-replay MCP server expose?
io.github.mdfifty50-boop/agent-replay exposes 8 tools: health_check, record_session, stop_recording, log_action, replay_session, and 3 more. Their descriptions and schemas cost roughly 421 tokens of context every time the server is loaded.
Is the io.github.mdfifty50-boop/agent-replay MCP server still maintained?
io.github.mdfifty50-boop/agent-replay is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.mdfifty50-boop/agent-replay MCP server under?
io.github.mdfifty50-boop/agent-replay declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.