# session-recap (npm · session-recap)

Recap AI coding sessions (Claude Code, Codex, dsh, OpenCode): intent, decisions, open threads.

- Trust score: 53/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `session-recap`: 53/100 (this document), [markdown](https://verifymcp.io/servers/brucexcluding-session-recap/session-recap.md), [page](https://verifymcp.io/servers/brucexcluding-session-recap/session-recap)

## Channel facts

- Registry: `npm`
- Package: `session-recap`
- Version: `0.6.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 516 tokens (~172/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the session-recap MCP server?

session-recap runs locally as an npm package, launched with npx -y session-recap mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add brucexcluding-session-recap -- npx -y session-recap mcp
```

### Cursor

```json
{
  "mcpServers": {
    "brucexcluding-session-recap": {
      "command": "npx",
      "args": [
        "-y",
        "session-recap",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "brucexcluding-session-recap": {
      "command": "npx",
      "args": [
        "-y",
        "session-recap",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add brucexcluding-session-recap -- npx -y session-recap mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "brucexcluding-session-recap": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "session-recap",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add brucexcluding-session-recap --command npx --arg -y --arg session-recap --arg mcp
```

### Hermes

```yaml
mcp_servers:
  brucexcluding-session-recap:
    command: "npx"
    args: ["-y", "session-recap", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "brucexcluding-session-recap": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "session-recap",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add brucexcluding-session-recap -t stdio -c npx -a -y session-recap mcp
```

### Other

```json
{
  "mcpServers": {
    "brucexcluding-session-recap": {
      "command": "npx",
      "args": [
        "-y",
        "session-recap",
        "mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 53)

First indexed and scored.

## MCP tools (3)

### `list_sessions` (~122 tokens)

List AI coding sessions

Lists saved sessions of Claude Code, Codex, dsh and OpenCode on this machine, newest first: agent, id, title, project folder, last activity. Filter by words in the title, by project folder, or by agent.

Input parameters:

- `agent` (string): Only this agent; "any" for all (default)
- `cwd` (string): Only sessions of this project folder (absolute path)
- `limit` (number): At most this many (default 20)
- `query` (string): Words in the title, or a session id

### `recap_session` (~239 tokens)

Recap a session

Recaps a coding session: intent, key decisions, what changed, open threads, where to resume. With no session given, the newest session of the calling agent in `cwd`. Returns a stored recap when the session has not changed since. Otherwise, if session-recap has a model configured it writes the recap; if not, it returns the condensed transcript and instructions, and you write the recap yourself and store it with save_recap.

Input parameters:

- `agent` (string): The agent whose sessions to look in; default: the caller
- `cwd` (string): The project folder you are working in (absolute path)
- `format` (string): "recap" (default: intent, decisions, changes, open threads, resume), "standup", "handoff" or "pr"
- `mode` (string): "agent": you write it; "model": session-recap writes it; "auto" (default): model if configured
- `refresh` (boolean): Write it again even if a stored recap is current
- `session` (string): A session id or words in its title; empty for the current session

### `save_recap` (~94 tokens)

Store a recap you wrote

Stores the recap you wrote for a session after recap_session returned its transcript, so the next recap of that session is reused or updated from it. Pass the agent, id and prompts recap_session gave you.

Input parameters:

- `agent` (string, required)
- `id` (string, required)
- `markdown` (string, required): The recap, in the format recap_session asked for
- `prompts` (number, required): The prompt count recap_session reported

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/brucexcluding-session-recap/session-recap#diagnostics

## Score history

- 2026-11-05: 53

## Common questions

### What is the session-recap MCP server?

session-recap is an MCP server listed in the public MCP registry as io.github.BruceXcluding/session-recap. Recap AI coding sessions (Claude Code, Codex, dsh, OpenCode): intent, decisions, open threads. This page covers its npm package (session-recap).

### Is the session-recap MCP server safe to use?

session-recap scores 53 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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 session-recap MCP server expose?

session-recap exposes 3 tools: list_sessions, recap_session, save_recap. Their descriptions and schemas cost roughly 455 tokens of context every time the server is loaded.

### Is the session-recap MCP server still maintained?

session-recap is still listed as active in the MCP registry. We last reached this channel on 5 November 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 session-recap MCP server under?

session-recap declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the session-recap MCP server?

VerifyMCP ran 14 checks on session-recap, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about session-recap: Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/session-recap
- Socket report: https://socket.dev/npm/package/session-recap
- Repository: https://github.com/BruceXcluding/session-recap
- Changelog RSS feed: https://verifymcp.io/servers/brucexcluding-session-recap/session-recap.xml
- Changelog JSON feed: https://verifymcp.io/servers/brucexcluding-session-recap/session-recap/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/brucexcluding-session-recap/session-recap.json
- HTML version of this page: https://verifymcp.io/servers/brucexcluding-session-recap/session-recap