Hypermarrow Mcp

io.github.qianqiuwanziPublished by GitHub account qianqiuwanziv0.1.1Updated Oct 24, 2026

Local-first AI memory MCP server. Record, recall and consolidate memory on your own machine.

The publisher's own server: 口播视频自动剪辑 MCP

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & Memory

Overview

AI-generated overview

A local-first AI memory server that lets an assistant record, recall and consolidate long-term context stored on your own machine.

What you can do
Record decisions, facts and preferences as persistent memory entries, and retrieve the most relevant past context when needed. Consolidate stored memory by merging duplicates and aging out stale entries. Map short names to local file paths so the assistant can refer to files by anchor.
When to use it
Useful when you want an assistant to carry context across sessions without a cloud memory service, such as remembering project decisions, preferences or file locations on a single desktop machine.
Requirements
Runs as a local stdio process, started with npx from the npm package hypermarrow-mcp, so Node.js is needed. Memory is written to a JSON file under the user's home directory. Optionally, an HYPERMARROW_ENDPOINT variable can point to a user-run backend.
Before you install
The server writes memory data to a local file, so anything recorded persists on disk and may be readable by others with access to that machine. Setting HYPERMARROW_ENDPOINT sends memory data to that backend, which is no longer local-only. File anchors store local file paths.

Installation

In SourceWeft

  1. Open Hypermarrow Mcp 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

HyperMarrow MCP Server

Local-first AI memory layer for the Model Context Protocol.

hypermarrow-mcp lets any MCP-compatible client read and write your long-term memory:

  • record_context – remember a decision, fact, or preference
  • recall_memory – retrieve the most relevant past context
  • consolidate – merge duplicates and age out stale entries
  • file_anchor – map a short name to a local file path

All memory lives under ~/.hypermarrow/memory.json on your own machine. Nothing is sent to the cloud unless you explicitly set HYPERMARROW_ENDPOINT to your own backend.

Install

bash
npx -y hypermarrow-mcp

Or add to your MCP client config:

json
{  "mcpServers": {    "hypermarrow": {      "command": "npx",      "args": ["-y", "hypermarrow-mcp"]    }  }}

Product

Privacy

Memory data is stored locally. The server only talks to the client over stdio and, optionally, to a user-configured HYPERMARROW_ENDPOINT. No telemetry, no cloud sync by default.

Source: README.md at commit 5823beb

Tools

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

Version history

1
  1. v0.1.1LatestSep 26, 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

Other Qianshi integrations

口播视频自动剪辑 MCP

cool.qianshiOfficial publisher

Cloud MCP for talking-head videos: plans a safe layout from your script and footage, then renders the finished clip and returns its URL.

Streamable HTTPWeb executable
Media & Design3 toolsOct 29, 2026