Pctx MCP Server

<div align="center"> <img src=".github/assets/logo.png" alt="PCTX Logo" style="height: 128px"> <h1>pctx</h1>

</div> <div align="center">

The open source framework to connect AI agents to tools and mcp with Code Mode

</div> <div align="center"> <br> _{— &nbsp; T R U S T E D &nbsp; B Y &nbsp; —} <br><br> <a href="https://goose-docs.ai/docs/guides/managing-tools/code-mode/"><picture><source media="(prefers-color-scheme: dark)" srcset=".github/assets/block-logo-white.png"><img src=".github/assets/block-logo.png" alt="Block" height="22"></picture></a> &nbsp;&nbsp;&nbsp;&nbsp; <a href="https://www.sentient.xyz"><picture><source media="(prefers-color-scheme: dark)" srcset=".github/assets/sentient-logo-white.svg"><img src=".github/assets/sentient-logo.svg" alt="Sentient" height="22"></picture></a> </div>

Install

# Homebrew
brew install portofcontext/tap/pctx

# cURL
curl --proto '=https' --tlsv1.2 -LsSf https://raw.githubusercontent.com/portofcontext/pctx/main/install.sh | sh

# npm
npm i -g @portofcontext/pctx

Core Functionality

pctx can be run as a scalable session server for Code Mode or as a lightweight unified MCP server that exposes Code Mode functionality for registered upstream MCP servers.

# Start the Code Mode session server for the Python SDK
pctx code-mode serve

# Start Code Mode as a unified MCP server
pctx code-mode init
pctx code-mode dev

Python SDK

Use the Python SDK if building agents in Python and want to run Code Mode with custom tools and/or MCP servers. The Python SDK is an HTTP client to the pctx server.

pip install pctx-client

from pctx_client import Pctx, tool
from agents import Agent # Use any Agent SDK
from agents.run import Runner # This example is OpenAI Agents SDK

@tool
def get_weather(city: str) -> str:
    """Get weather information for a given city."""
    return f"It's always sunny in {city}!"

pctx = Pctx(tools=[get_weather]) # or with mcp: servers=[your_mcp]

tools = pctx.openai_agents_tools() # Run Code Mode with any Agent SDK
agent = Agent(
    name="GreatCoder",
    model="litellm/openrouter/openai/gpt-oss-120b",
    instructions="You run code to complete complex tasks.",
    tools=tools,
)

Links

• Python SDK Quickstart and Docs
• Python API Reference

Node SDK

Coming soon

Unified MCP

Use the unified MCP to run Code Mode with MCP servers and want to persist the authentication connections and you do not need to use agent tools (non-mcp tools).

# Initialize config for upstream mcp connections
pctx code-mode init

# Add HTTP or stdio MCP servers
pctx code-mode add stripe https://mcp.stripe.com
pctx code-mode add memory --command "npx -y @modelcontextprotocol/server-memory"

# Start as HTTP server (dev mode with UI)
pctx code-mode dev

# Or start as stdio MCP server
pctx code-mode start --stdio

For complete CLI documentation, see CLI.md. For configuration options, see Configuration Guide.

<img width="1020" height="757" alt="Screenshot 2025-11-21 at 11 03 20 AM" src="https://github.com/user-attachments/assets/d61be46d-5a4b-40fd-953a-7dc725266e63" />

What is pctx?

pctx sits between AI agents and MCP servers. It aggregates multiple upstream MCP servers, handles authentication, and exposes tools through a unified Code Mode interface. Instead of agents managing connections to individual MCP servers, they connect once to pctx.

What is Code Mode?

Code mode replaces sequential tool calling with code execution. Rather than an agent calling tools one at a time and passing results through its context window, it writes code that executes in a sandbox. Read Anthropic's overview here.

Traditional MCP flow:

1. Agent calls getSheet(id)
2. Server returns 1000 rows → agent's context
3. Agent calls filterRows(criteria)
4. Server returns 50 rows → agent's context

With Code Mode:

const sheet = await gdrive.getSheet({ sheetId: "abc" });
const orders = sheet.filter((row) => row.status === "pending");
console.log(`Found ${orders.length} orders`);

Result: 98.7% reduction in tokens (150k → 2k) for this multi-step operation.

Features

• Code Mode interface: Tools exposed as code functions for efficient agent interaction. See Code Mode Guide.
• Upstream MCP server aggregation: Connect to multiple MCP servers through a single interface, with persistent upstream sessions across execute_typescript calls. See Upstream MCP Servers Guide.
• Simple config with CLI: Create the pctx.json config with a simple CLI. pctx.json manages auth, upstream MCPs, logging, and more. See Config Guide.
• Secure authentication: Source secrets from environment variables, system keychain, and external commands. See Authentication Section in the CLI configuration docs for more details.

Security

• LLM generated code runs in an isolated Deno sandbox that can only access the network hosts specified in the configuration file.
• No filesystem, environment, network (beyond allowed hosts), or system access.
• MCP clients are authenticated in pctx. LLMs can never see your auth.

Update

Depending on the installation method (Homebrew/npm/cURL) the update method is different. Run which pctx if you are unsure what you used to install it.

# Homebrew update
brew upgrade pctx

# cURL update
pctx-update

# npm update
npm upgrade -g @portofcontext/pctx

Develop

• For core dev: install rust and jump into crates/
• Client SDK dev: find the README in the SDK

Learn More

• Model Context Protocol (MCP)
• Code execution with MCP by Anthropic
• Code Mode explanation by Cloudflare