MCP servers · brucexcluding

session-recap: structured recaps of AI coding sessions

An MCP server, local viewer, CLI and plugins that read AI coding session transcripts and write structured recaps of them.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

session-recap reads the full transcript of an AI coding session and produces a short structured recap. The recap covers the intent of the session, key decisions and rejected alternatives, what changed, open threads, and where to resume. Each recap also includes a Map of the phases the work went through, with the key decisions and lists of what shipped, what is open and what was dropped. It reads sessions from Claude Code, Codex, dsh and OpenCode.

It suits long-running projects where sessions pile up across several agents, or where a session from weeks earlier needs to be picked up again. It can be used from any MCP client, from a local viewer that lists every agent's sessions by project, from the command line, or through plugins for Claude Code, dsh and Codex. The command line can also output a standup note, a handoff or a pull request summary instead of a recap.

Through MCP, the agent you are working with writes the recap using its own model, so no separate API key is needed. A model configured for session-recap is optional and is used by the command line and the viewer's Write recap feature. Sessions are read on the local machine, and secrets are removed before any text is sent to a model. A dry-run option shows the size that would be sent and how many secrets were removed, without calling a model.

Limitations and requirements

Requires Node.js 20 or later and python3. Sessions from dsh need the zstd command or Python 3.14 or later. Codex review threads and dsh subagent sessions are not read. Using the command line or the viewer's Write recap feature requires a configured model provider and its API key. Recaps are sent to that model when generated.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    session-recap

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

    v0.6.1
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 18 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 18 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 18 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 18 Nov 2026