LynxPrompt

io.github.GeiserXPublished by GitHub account GeiserXv0.3.0Updated Oct 29, 2026

Search, read and manage AI agent instruction blueprints (AGENTS.md, CLAUDE.md) on LynxPrompt

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

MCP server for LynxPrompt instances that lets an assistant search, read and manage AI agent instruction blueprints such as AGENTS.md and CLAUDE.md.

What you can do
  • Search the public blueprint marketplace and list your own blueprints and hierarchies
  • Read any blueprint you can see, plus hierarchies flat and as a tree, and read-only resources
  • Create and update blueprints, including publishing them publicly
  • Delete blueprints and hierarchies, with checksum-guarded updates
When to use it
Use it when you keep AI agent instruction files in LynxPrompt, self-hosted or hosted, and want an assistant to look up, compare or edit those blueprints and monorepo hierarchies without leaving the chat.
Requirements
Runs locally over stdio via npx or Docker. Needs a LynxPrompt API token in LYNXPROMPT_TOKEN, created under Settings > API tokens; the token is required for every tool except search_blueprints. For a self-hosted instance, set LYNXPROMPT_URL. Network access to the instance is required.
Before you install
The token grants access to your LynxPrompt account, so keep it out of shared configs. Write tools create, overwrite and permanently delete blueprints and hierarchies, and create_blueprint with PUBLIC visibility publishes content to the marketplace. Set LYNXPROMPT_READ_ONLY=true to register only read tools. Blueprint content is sent to the configured instance.

Installation

In SourceWeft

  1. Open LynxPrompt 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

[lynxprompt-mcp]

lynxprompt-mcp

[npm] [CI] [codecov] [Docker Pulls] [License]

An MCP server for any LynxPrompt instance. LLMs use it to browse, search and manage AI configuration blueprints.

It works with lynxprompt.geiser.cloud or your own self-hosted LynxPrompt, over HTTP or stdio.

Features

  • Tools to search the public marketplace, list your own blueprints and hierarchies, read any blueprint you can see, and create, update and delete them. Every tool carries a title, read-only/destructive hints and an output schema.
  • update_blueprint takes the content_checksum from get_blueprint as expected_checksum, so it never silently overwrites an edit made elsewhere.
  • LYNXPROMPT_READ_ONLY=true registers only the read tools.
  • Read-only resources too: lynxprompt://blueprints, lynxprompt://blueprint/{id}, lynxprompt://hierarchies, lynxprompt://hierarchy/{id}, lynxprompt://user.
  • Speaks MCP 2026-07-28 and every earlier revision down to 2024-11-05 from the same binary, so current clients (which still use the initialize handshake) and 2026-07-28 clients both work.
  • stdio, or stateless Streamable HTTP on /mcp with Origin checks, a body limit and bearer auth when exposed.
  • Ships as an npm package (npx lynxprompt-mcp), a Docker image and multi-arch Go binaries.

Tools

ToolWhat it doesChanges data
search_blueprintsSearch the public marketplace (query, configs/commands, category, tags, sort, page)no
list_blueprintsYour blueprints, paged, filter by visibilityno
get_blueprintAny blueprint you can see (yours, your team's, public) with content and content_checksumno
list_hierarchiesYour hierarchies (monorepo groupings), pagedno
get_hierarchyOne hierarchy with its blueprints, flat and as a treeno
create_blueprintNew blueprint; visibility: PUBLIC publishes ityes
update_blueprintChange fields; pass expected_checksumyes, overwrites
delete_blueprintPermanent deleteyes, destructive
create_hierarchyNew hierarchy; returns the existing one for the same repository_rootyes
delete_hierarchyDelete a hierarchy; its blueprints are kept, unlinkedyes, destructive

Install

Create an API token on your LynxPrompt instance under Settings, API tokens. For a self-hosted instance also set LYNXPROMPT_URL. Add LYNXPROMPT_READ_ONLY=true to hide the write tools.

Claude Code

sh
claude mcp add lynxprompt --scope user --env LYNXPROMPT_TOKEN=lp_... -- npx -y lynxprompt-mcp

Claude Desktop (claude_desktop_config.json) and Cursor (~/.cursor/mcp.json)

json
{  "mcpServers": {    "lynxprompt": {      "command": "npx",      "args": ["-y", "lynxprompt-mcp"],      "env": { "LYNXPROMPT_TOKEN": "lp_..." }    }  }}

VS Code (.vscode/mcp.json, asks for the token once and stores it encrypted)

json
{  "inputs": [    { "type": "promptString", "id": "lynxprompt-token", "description": "LynxPrompt API token", "password": true }  ],  "servers": {    "lynxprompt": {      "type": "stdio",      "command": "npx",      "args": ["-y", "lynxprompt-mcp"],      "env": { "LYNXPROMPT_TOKEN": "${input:lynxprompt-token}" }    }  }}

Codex (~/.codex/config.toml)

toml
[mcp_servers.lynxprompt]command = "npx"args = ["-y", "lynxprompt-mcp"]env = { LYNXPROMPT_TOKEN = "lp_..." }

Docker (stdio, any client): command docker, args ["run", "-i", "--rm", "-e", "TRANSPORT=stdio", "-e", "LYNXPROMPT_TOKEN", "drumsergio/lynxprompt-mcp:v0.2.0"].

The npm package downloads the release binary on first run and checks its sha256 against the checksums shipped inside the package. The HTTP server, Docker Compose and local builds are in Getting started.

Documentation

Related projects

LynxPrompt, the self-hosted platform this server talks to.

License

GPL-3.0-or-later

Source: README.md at commit 70d7444

Tools

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

Version history

4
  1. v0.3.0LatestOct 29, 2026
  2. v0.1.2Oct 21, 2026
  3. v0.1.1Oct 5, 2026
  4. v0.0.2Sep 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