YouTipCodex Mcp
MCP (Model Context Protocol) allows Codex to integrate with external tools and services.
This section details how to configure and use MCP servers.
* * *
## What is MCP?
MCP is an open protocol that enables standardized interaction between AI models and external tools and services. Through MCP servers, you can extend Codex's capabilities:
!(#)
* Connect to file system
* Access databases
* Integrate project management tools
* Call external APIs
> MCP is built on the open (https://modelcontextprotocol.io/), supporting standardized integration across different tools.
* * *
## MCP Basic Configuration
### Codex Configuration Menu
You can manage or add MCP services through the settings menu:
!(#)
Connect to custom MCP:
!(#)
### Configuration File Location
MCP servers are configured in the `mcp_servers` section of `~/.codex/config.toml`.
### stdio Type Servers
## Configure stdio MCP Server
[mcp_servers.filesystem]
# Server startup command
command = "npx"
# Arguments passed to the command
args = ["-y", "@modelcontextprotocol/server-filesystem", "./docs"]
# Server working directory
cwd = "/path/to/workdir"
# Pass environment variables
env = {
NODE_ENV = "production"
}
### HTTP Type Servers
## Configure HTTP MCP Server
[mcp_servers.docs]
# MCP HTTP server endpoint
url = "https://docs.example.com/mcp"
# HTTP headers to include
http_headers = {
Authorization = "Bearer token"
}
* * *
## MCP Tool Configuration
### Limit Available Tools
You can limit the tools exposed by MCP servers:
## Tool Whitelist/Blacklist
[mcp_servers.filesystem]
# List of allowed tools
enabled_tools = ["read_file", "write_file", "list_directory"]
# List of denied tools (applied after enabled_tools)
disabled_tools =
> Using tool restrictions can improve security by only exposing the tools you need.
### Timeout Configuration
## Configure Timeout
[mcp_servers.slow_server]
command = "python"
args = ["-m", "slow_server"]
# Startup timeout (seconds, default 10)
startup_timeout_sec = 30
# Per-tool call timeout (seconds, default 60)
tool_timeout_sec = 120
* * *
## MCP Authentication Configuration
### OAuth Configuration
## Configure OAuth
[mcp_servers.protected]
url = "https://api.example.com/mcp"
# Requested OAuth scopes
scopes = ["read", "write"]
# OAuth resource parameter
oauth_resource = "codex-integration"
# Bearer token environment variable
bearer_token_env_var = "EXAMPLE_API_TOKEN"
### HTTP Header Configuration
## Configure HTTP Headers
[mcp_servers.api]
url = "https://api.example.com/mcp"
# HTTP headers populated from environment variables
env_http_headers = {
X_API_KEY = "MY_API_KEY"
}
# Static HTTP headers
http_headers = {
X_Custom_Header = "value"
}
* * *
### OAuth Callback Configuration
## Configure OAuth Callback
# Fixed callback port
mcp_oauth_callback_port = 8080
# Custom callback URL
mcp_oauth_callback_url = "https://my-devbox.example.com/callback"
# Credentials storage location
mcp_oauth_credentials_store = "keyring" # file | keyring | auto
* * *
## MCP Tool Permissions
You can set permissions for each tool of each MCP server separately:
## Configure Tool Permissions
[mcp_servers.docs.tools.search]
# Permission mode: ask | approve | deny
approval_mode = "approve"
| Permission Mode | Description |
| --- | --- |
| `ask` | Ask before each execution (default) |
| `approve` | Auto-approve |
| `deny` | Auto-deny |
> Be careful when configuring tool permissions, ensuring you only grant auto-approval permissions to tools you trust.
* * *
## Common MCP Servers
### File System Server
## File System MCP
[mcp_servers.filesystem]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-filesystem", "./docs"]
### GitHub Server
## GitHub MCP
[mcp_servers.github]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-github"]
env = {
GITHUB_PERSONAL_ACCESS_TOKEN = "your-token-here"
}
### PostgreSQL Server
## PostgreSQL MCP
[mcp_servers.postgres]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-postgres", "postgresql://user:pass@localhost/db"]
* * *
## Common MCP Servers
You can install more MCP servers via npm:
# Search MCP servers
npm search @modelcontextprotocol/server
# Install MCP servers
npm install -g @modelcontextprotocol/server-filesystem
> OpenAI officially provides various MCP servers. Check the (https://github.com/modelcontextprotocol/servers) for the complete list.
* * *
## Troubleshooting
### Server Startup Failure
Check the following:
* Whether the command and arguments are correct
* Whether necessary dependencies are installed
* Whether environment variables are set correctly
### Tool Call Timeout
Increase the timeout:
tool_timeout_sec = 120
### Authentication Issues
Ensure the OAuth callback port is not occupied and the credentials storage configuration is correct.
> Use `codex --verbose` to view detailed MCP debugging information.
* * *
## FAQ
### Q: MCP server cannot start?
Check if the command is correctly installed and try running the command manually to confirm there are no errors.
### Q: Where to configure tool permissions?
Configure in the `mcp_servers..tools.` section of the configuration file.
### Q: How to disable an MCP server?
Add `enabled = false` in the configuration or delete the configuration directly.
### Q: How many MCP servers are supported?
There is no strict limit, but it is recommended to only configure the servers you actually need.