Memocall

io.github.baodq06Published by GitHub account baodq06v0.1.0Updated Oct 24, 2026

Recall past Claude Code conversations from any project as clean, compact Markdown.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

A local MCP server that lets Claude Code recall past conversations from any project as compact Markdown transcripts.

What you can do
  • List recent sessions across all projects, grouped by directory
  • Search past conversations by keyword across titles, first messages and paths
  • Load a single session as compact Markdown, optionally limited to a turn range
  • Outline a large session as a numbered list of prompts
  • Search within one session and return only matching turns
When to use it
Useful when you want the assistant to pick up context from an earlier Claude Code session, even one from a different project, instead of copy-pasting exports or digging through raw transcript files. Also helps navigate very large sessions by outline and turn ranges.
Requirements
Runs locally over stdio via npx (Node 18+), installed with the Claude Code CLI at user scope. It reads transcript files under the Claude Code projects directory and needs no network, auth, API keys or environment variables.
Before you install
Loaded transcripts can contain secrets from earlier conversations; the default compact mode elides tool outputs, but the full format includes brief tool inputs and may surface sensitive strings. Treat recalled context as you would the original conversation. Recall is best-effort because Claude Code deletes transcripts after its cleanup period, and the undocumented transcript format may change between versions.

Installation

In SourceWeft

  1. Open Memocall in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

MemoCall

An MCP server that lets Claude Code recall the context of your past conversations — from any project — on demand.

Claude Code can resume a session, but getting another conversation's context into the one you're in is a chore — copy-pasting exports or digging through raw transcript files by hand — and resume only sees the current directory anyway. MemoCall turns it into a single ask: "what was I working on?" or "load the session where we set up X", and it pulls that transcript in as clean, compact Markdown — even from a totally different project.

It's read-only. Claude Code already records every session to ~/.claude/projects/<project>/<id>.jsonl; this server just reads those files, strips the noise, collapses tool calls, and hands back a readable transcript. It never writes, hooks, or touches a live session.

What you get

Five tools, available in every session once installed. Claude picks the right one from the request:

ToolWhat it does
list_sessionsYour recent conversations across all projects, grouped by directory. "What was I working on?"
search_sessionsFind a past conversation by keyword (matches titles + first messages + paths).
load_sessionLoad one conversation as compact Markdown — by id or query. Optionally a turn window via turns.
session_outlineA cheap map of one conversation: the numbered list of your prompts. Great for huge sessions.
search_in_sessionReturn only the turns within one conversation that match a keyword.

You don't call these directly — you talk normally and Claude reaches for them:

You:  what sessions have i worked on recently?You:  load the one where we set up the license invitation systemYou:  which session did we debug the keychain SIGKILL thing in?

How the transcript is rendered

Raw transcripts are a verbose event log (one big file hit 11 MB). memocall reduces each turn to the essentials, Conductor-style:

**You:** right now i need to set up a system to invite prospects...↳ 12 tool calls (Bash ×5, Read ×4, Edit ×3)**Claude:** I've set up the invitation flow. Key decisions: ...

Tool-call outputs are elided (the big token win, and a privacy win — see below). Abandoned/edited message branches are dropped so you get the conversation as it actually played out. A token budget keeps even an 11 MB session well under Claude Code's MCP output cap via middle-out truncation.

Navigating large sessions

A single response can't hold a 1,000-turn session, so for big ones you don't dump — you navigate:

  1. session_outline → a numbered map of every prompt (tiny, fits any session).
  2. search_in_session → jump straight to the turns about a topic, or load_session with turns: "300-340" to pull an exact window (turn numbers come from the outline).

So you never lose access to the middle of a huge conversation — load_session alone would middle-out-truncate it, but the outline + range/search tools let Claude reach any part on demand.

Install

Requires the Claude Code CLI (and Node 18+). One line — npx fetches and runs the published package:

bash
claude mcp add --scope user memocall -- npx -y memocall

--scope user makes it available in every session, in every directory. Restart Claude Code (or open a new session) and ask it to list your sessions. Verify with claude mcp list — you should see memocall: … ✔ Connected.

Or run from source (for development)
bash
git clone https://github.com/baodq06/memocall.gitcd memocall && npm install && npm run buildclaude mcp add --scope user memocall -- node "$(pwd)/dist/index.js"

Privacy & security

  • Local only. No network, no auth, no telemetry. It reads files under ~/.claude/projects/ and nothing else.
  • Compact mode elides tool outputs, which is where secrets (tokens, keys, env) usually live — so the default output is much safer than the raw transcript.
  • format: "full" includes brief tool inputs and may surface sensitive strings. Use it deliberately.
  • Transcripts can contain secrets regardless; treat loaded context as you would the original conversation.

Limitations

  • Recall is best-effort: Claude Code deletes transcripts after cleanupPeriodDays (default 30).
  • Forked sessions may only contain post-fork turns.
  • The transcript format is undocumented and can change between Claude Code versions; all format knowledge is isolated in src/jsonl.ts so it's a one-file patch if it does.

Development

bash
npm run build           # compile TypeScript -> dist/npm test                # unit suite (node:test) on synthetic fixturesnpm run smoke           # optional: checks all YOUR real sessions stay under the output capnode dist/parser.js <file.jsonl> [--full|--outline] [--turns 10-20] [--search "kw"] [--max N] [--think]   # test the parsernode test-client.mjs    # drive the server over stdio like Claude Code doesnpm run inspect         # open the MCP Inspector UI

Layout:

  • src/jsonl.ts — all knowledge of the transcript format (helpers, ordering, classification).
  • src/parser.ts — JSONL → compact Markdown (the core transform).
  • src/locator.ts — session enumeration + cached metadata index.
  • src/index.ts — the MCP server wiring the three tools.

License

MIT

Source: README.md at commit 53276bd

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts