Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.constripacity/claude-replay

PYPI · CLAUDE-REPLAY · SCANNED SEP 20

Session checkpoint & recovery for Claude Code: resume, search, tag, and export recorded sessions.

Available components

0 this week 81 Trust /100
Trust breakdown (7 categories)

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency32
Schema Quality & AI Usability80
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 639 tokens (~63/item across 10 items; 10 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 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
Install

How do I install the io.github.constripacity/claude-replay MCP server?

io.github.constripacity/claude-replay runs locally as a PyPI package, launched with uvx claude-replay. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · claude-replay

# add to Claude Code
claude mcp add constripacity-claude-replay -- uvx claude-replay
// .cursor/mcp.json
{
  "mcpServers": {
    "constripacity-claude-replay": {
      "command": "uvx",
      "args": [
        "claude-replay"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "constripacity-claude-replay": {
      "command": "uvx",
      "args": [
        "claude-replay"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add constripacity-claude-replay -- uvx claude-replay
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "constripacity-claude-replay": {
      "type": "local",
      "command": [
        "uvx",
        "claude-replay"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add constripacity-claude-replay --command uvx --arg claude-replay
# ~/.hermes/config.yaml
mcp_servers:
  constripacity-claude-replay:
    command: "uvx"
    args: ["claude-replay"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "constripacity-claude-replay": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "claude-replay"
      ]
    }
  }
}
# add to Vellum
assistant mcp add constripacity-claude-replay -t stdio -c uvx -a claude-replay
// mcp.json
{
  "mcpServers": {
    "constripacity-claude-replay": {
      "command": "uvx",
      "args": [
        "claude-replay"
      ]
    }
  }
}
Changelog

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.

  • 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 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 +1
    • Stability: 0.97 → pass security
  • 14 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.

  • 12 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.

  • 11 Sept 26 0
    • Security disclosure: unverified → fail functional
  • 10 Sept 26 0
    • Security disclosure: fail → unverified functional
  • 9 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

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 20 Sept 2026 · Analysed pypi/claude-replay@0.4.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 29 packages
Packages resolved 29
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 10 exposed · ~639 tokens

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 →

Tool Tokens
replay_checkpoint ~35

Force a checkpoint of the current session right now, with an optional note.

NameTypeReqDescription
notestringOptional note describing the checkpoint

No output schema declared.

No examples provided.

replay_diff ~56

Compare two sessions side by side: metric deltas (tool calls, errors, duration, files) and which files each touched.

NameTypeReqDescription
session_astringyesFirst session ID
session_bstringyesSecond session ID

No output schema declared.

No examples provided.

replay_export ~77

Render a session as a self-contained trace (html, json, or md) and return the output path.

NameTypeReqDescription
formatstringExport format (default: html)
outputstringOutput directory (default: ~/.claude-replay/exports)
session_idstringSession ID (default: most recent)

No output schema declared.

No examples provided.

replay_insights ~53

Per-session insight metrics: how it ended, duration, tool-call count, error count/rate, files touched, and the most-used tools.

NameTypeReqDescription
session_idstringSession ID (default: most recent)

No output schema declared.

No examples provided.

replay_resume ~54

Generate a structured resume brief for a session (default: the most recent). Paste the result into a new Claude Code session to continue where it left off.

NameTypeReqDescription
session_idstringSession ID (default: most recent)

No output schema declared.

No examples provided.

replay_search ~142

Full-text search across recorded sessions (event payloads, objective, name, and tags), with optional filters. Ranked by match count. Omit the query to browse by filters alone.

NameTypeReqDescription
causestringOnly sessions with this death cause
limitintegerMax sessions (default: 20)
projectstringOnly sessions whose project dir contains this
querystringText to search for (optional if filtering)
sincestringOnly sessions started after this ISO date
toolstringOnly sessions that used this tool
untilstringOnly sessions started before this ISO date

No output schema declared.

No examples provided.

replay_sessions ~38

List recent sessions with status, model, duration, and checkpoint count.

NameTypeReqDescription
limitintegerMax sessions to list (default: 10)

No output schema declared.

No examples provided.

replay_stats ~80

Cross-session analytics across all recorded sessions: total tool calls, overall error rate, why sessions end (death-cause breakdown), the tool mix, and per-project rollups. Optional limit / project filter.

NameTypeReqDescription
limitintegerOnly the N most recent sessions (default: all)
projectstringOnly sessions whose project dir contains this

No output schema declared.

No examples provided.

replay_status ~23

Current session summary: objective, status, checkpoint/event counts, last activity.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

replay_tag ~81

Name or tag a session for later retrieval. Sets a name and/or adds/removes tags on a session (default: the most recent).

NameTypeReqDescription
addarrayTags to add
namestringHuman-friendly name
removearrayTags to remove
session_idstringSession ID (default: most recent)

No output schema declared.

No examples provided.

Common questions

What is the io.github.constripacity/claude-replay MCP server?

io.github.constripacity/claude-replay is an MCP server listed in the public MCP registry as io.github.constripacity/claude-replay. Session checkpoint & recovery for Claude Code: resume, search, tag, and export recorded sessions. This page covers its PyPI package (claude-replay).

Is the io.github.constripacity/claude-replay MCP server safe to use?

io.github.constripacity/claude-replay scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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.constripacity/claude-replay MCP server expose?

io.github.constripacity/claude-replay exposes 10 tools: replay_status, replay_checkpoint, replay_resume, replay_sessions, replay_export, and 5 more. Their descriptions and schemas cost roughly 639 tokens of context every time the server is loaded.

Is the io.github.constripacity/claude-replay MCP server still maintained?

io.github.constripacity/claude-replay is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.