Campfire MCP
Connects a local Codex session to SMS so users can check and acknowledge inbound messages and send concise updates from a phone.
README
Campfire MCP
Campfire MCP connects a local Codex session to the Campfire SMS transport. Campfire carries messages; your Codex runtime supplies the model, tools, and permissions.
Install on Windows
Requires Python 3.12 or newer.
py -m pip install "campfire-mcp @ https://github.com/campfiresms/campfire-mcp/archive/refs/tags/v0.1.1.zip"
py -m campfire_mcp.cli configure
configure asks for the service URL and the one-time installation credential
shown after signup. It stores the credential under your local user profile with
restricted permissions, validates it with Campfire, and registers the STDIO
server through codex mcp add when the Codex CLI is available.
Restart ChatGPT desktop, Codex CLI, or the IDE extension after configuration.
The clients share the same Codex MCP configuration on a host. You can inspect
the connection with /mcp or:
codex mcp list
py -m campfire_mcp.cli status
Then ask Codex to open the Campfire bridge. While the Codex session is active, use the Campfire tools to check and acknowledge inbound SMS or send a concise SMS update.
Trust boundary
A message matching the enrolled number means Campfire verified control of that number during enrollment and received this message through an authenticated provider webhook. It is not permanent proof of human identity.
Campfire SMS is a lower-trust steering channel. It cannot grant tools, permissions, credentials, secret disclosure, destructive authority, or replace Codex's native approval system. SMS is not end-to-end encrypted; do not send passwords, payment details, or sensitive data.
Commands
py -m campfire_mcp.cli configure Save and validate this installation
py -m campfire_mcp.cli status Validate the saved credential and service
py -m campfire_mcp.cli serve Run the STDIO MCP server
Advanced users may set CAMPFIRE_API_URL, CAMPFIRE_CREDENTIAL,
CAMPFIRE_CONFIG_PATH, and CAMPFIRE_BRIDGE_STATE_PATH. Environment values
override the saved local configuration.
Remove
Revoke the installation from Campfire setup, then run:
codex mcp remove campfire
py -m pip uninstall campfire-mcp
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.