Model Context Protocol
The Anthropic Model Context Protocol (MCP) is an open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools.
You can configure a reference to an MCP configuration file in the Oxygen XML page. AI Positron utilizes this file to load extra tools that can be called by the AI engine when using the chat modes or when invoking custom AI actions.
The following options are available:
- Allow running local MCP servers
- Selecting this option allows local MCP servers to run as external processes.Attention:Local MCP servers are run as processes from the current user account and have full access to the computer resources as all other processes run in the user account. Before enabling this option, you need to ensure that your configuration starts a secure MCP server and does not expose you to security risks.
- Configuration file
-
A reference to a JSON file that configures MCP servers of three possible types:
- Local process
- HTTP SSE
- HTTP Streamable
Configuration file examples:-
Configuration of a local MCP server that adds tools to allow the AI to use the Brave engine to perform web searches:
{ "mcpServers": { "brave-search": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-brave-search" ], "env": { "BRAVE_API_KEY": "API_KEY_HERE" } } }
- Configuration of a remote MCP HTTP SSE server that adds
tools to allow the AI to call the DeepWiki service and obtain information about
various GitHub
projects:
If the HTTP SSE server has a URL that does not end with{ "mcpServers": { "deepwiki": { "url":"https://mcp.deepwiki.com/sse" } } }
/sse
, then an extra"type":"sse"
property must be added in the configuration. - Configuration of a remote MCP Streamable HTTP server that adds tools to allow
the AI to call the DeepWiki service and obtain
information about various GitHub
projects:
{ "mcpServers": { "deepwiki": { "url":"https://mcp.deepwiki.com/mcp" } } }
- Multiple MCP servers (Brave search, GitHub, DeepWiki) configured in the same
file:
{ "mcpServers": { "brave-search": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-brave-search" ], "env": { "BRAVE_API_KEY": "API_KEY_HERE" } }, "github": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server" ], "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "API_KEY_HERE" } }, "deepwiki": { "url":"https://mcp.deepwiki.com/sse" } } }
- Starting an Atlassian JIRA HTTP SSE MCP server with
the
command:
and then using it as a remote SSE server in the configuration file:uvx mcp-atlassian --jira-url https://our.jira.server.url --jira-personal-token MY_TOKEN_HERE --transport sse --port 8000 --read-only --verbose
{ "mcpServers": { "atlassian-sse": { "url": "http://our.jira.server.url:8000/sse" } } }
- Starting an Atlassian JIRA Streamable HTTP MCP server
with the
command:
and then using it as a remote SSE server in the configuration file:uvx mcp-atlassian --jira-url https://our.jira.server.url --jira-personal-token MY_TOKEN_HERE --transport streamable-http --port 8000 --read-only --verbose
To pass HTTP header properties to the server, you can use the{ "mcpServers": { "atlassian": { "url": "http://our.jira.server.url:8000/mcp" } } }
env
property like this:{ "mcpServers": { "atlassian": { "url": "http://our.jira.server.url:8000/mcp", "env": { "Authorization": "Bearer SOME_KEY_VALUE_HERE" } } } }
- Connection timeout (seconds)
- The configured timeout for attempts to connect to each server or retrieve content from it.
- Add provided tools to all chat modes
- Enabled by default, this option allows all defined chat modes to access the tools provided by the MCP servers during conversations.
- Connection status
- Presents the status of each MCP server connection and the tools that have been retrieved from it.