affinity-mcp-proxy
Proxies the local Affinity MCP server over stdio, enabling tools to call Affinity's tools like execute_script and search_sdk_hints via MCP.
README
affinity-mcp-proxy
affinity-mcp-proxy exposes the local Affinity MCP server as an MCP server over stdio.
It is designed for tools that know how to launch MCP servers as local commands, for example:
{
"mcpServers": {
"affinity": {
"command": "pnpm",
"args": ["dlx", "affinity-mcp-proxy"]
}
}
}
What it does
- connects to the local Affinity MCP server over HTTP/SSE
- re-exposes
tools/listandtools/calloverstdio - primes
execute_scriptwithread_preamblein the same upstream session - ships a small CLI for diagnostics and direct tool calls
Status
- first-class target: macOS
- runtime: Node.js 22+
- package manager:
pnpm
Other platforms may work, but this package is only validated on macOS in the first release.
Install and run
Preferred ephemeral usage:
pnpm dlx affinity-mcp-proxy
Direct CLI usage:
pnpm dlx --package affinity-mcp-proxy affinity-mcp-proxy-cli list-tools
pnpm dlx --package affinity-mcp-proxy affinity-mcp-proxy-cli call-tool search_sdk_hints '{"query":"text style"}'
Local development:
pnpm install
pnpm test
pnpm dlx . --help
node ./affinity_mcp_proxy.mjs --help
Requirements
- Affinity must be open
- the local Affinity MCP server must be enabled and listening
- Node.js 22 or newer
By default the proxy tries these upstream URLs:
http://127.0.0.1:6767/ssehttp://127.0.0.1:6767http://[::1]:6767/ssehttp://[::1]:6767
Environment variables
AFFINITY_MCP_URL- force a specific upstream MCP URL
AFFINITY_MCP_CONNECT_TIMEOUT_MS- override the connection timeout
AFFINITY_MCP_DEBUG- enable proxy debug logs on
stderr
- enable proxy debug logs on
The proxy requires the SDK to be installed through the package dependencies. There is no alternate local SDK fallback.
Commands
Proxy server:
pnpm dlx affinity-mcp-proxy
pnpm dlx affinity-mcp-proxy --help
pnpm dlx affinity-mcp-proxy --version
Diagnostic CLI:
pnpm dlx --package affinity-mcp-proxy affinity-mcp-proxy-cli list-tools
pnpm dlx --package affinity-mcp-proxy affinity-mcp-proxy-cli execute-script-file ./script.js
pnpm dlx --package affinity-mcp-proxy affinity-mcp-proxy-cli render-spread-file DOCUMENT_SESSION_UUID '{"spread_index":2,"out":"/tmp/spread-2.jpg"}'
Troubleshooting
If the proxy exits immediately:
- confirm Affinity is open
- confirm the local MCP endpoint is enabled
- set
AFFINITY_MCP_DEBUG=1to see connection attempts - if your environment prefers a specific interface, set
AFFINITY_MCP_URLexplicitly
If text formatting scripts fail inside Affinity with COMMAND_FAILED, make sure the script sets the current spread to the target text node spread before calling doc.formatText(...).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.