Skip to main content
Connect Gammacode to tools via MCP and extend your development capabilities.
Gammacode can connect to hundreds of external tools and data sources through the Model Context Protocol (MCP), an open-source standard for AI-tool integrations. MCP servers give Gammacode access to your tools, databases, and APIs.

​
What you can do with MCP

With MCP servers connected, you can ask Gammacode to:
  • Implement features from issue trackers: “Add the feature described in JIRA issue ENG-4521 and create a PR on GitHub.”
  • Analyze monitoring data: “Check Sentry and Statsig to check the usage of the feature described in ENG-4521.”
  • Query databases: “Find emails of 10 random users who used feature ENG-4521, based on our Postgres database.”
  • Integrate designs: “Update our standard email template based on the new Figma designs that were posted in Slack”
  • Automate workflows: “Create Gmail drafts inviting these 10 users to a feedback session about the new feature.”
Here are some commonly used MCP servers you can connect to Gammacode:
Use third party MCP servers at your own risk - we have not verified the correctness or security of all these servers. Make sure you trust MCP servers you are installing. Be especially careful when using MCP servers that could fetch untrusted content, as these can expose you to prompt injection risk.

​
Development & Testing Tools

Sentry - Monitor errors, debug production issues Socket - Security analysis for dependencies Hugging Face - Access to Hugging Face Hub information and Gradio AI Applications Jam - Debug faster with AI agents that can access Jam recordings like video, console logs, network requests, and errors

​
Project Management & Documentation

Notion - Read docs, update pages, manage tasks Linear - Integrate with Linear’s issue tracking and project management Atlassian - Manage your Jira tickets and Confluence docs Asana - Interact with your Asana workspace to keep projects on track Monday - Manage monday.com boards by creating items, updating columns, assigning owners

​
Design & Media

Figma - Generate better code by bringing in full Figma context Canva - Browse, summarize, autofill, and even generate new Canva designs directly from Claude invideo - Build video creation capabilities into your applications

​
Infrastructure & DevOps

Vercel - Vercel’s official MCP server, allowing you to search and navigate documentation, manage projects and deployments Netlify - Create, deploy, and manage websites on Netlify Cloudflare - Build applications, analyze traffic, monitor performance, and manage security settings

​
Payments & Commerce

Stripe - Payment processing, subscription management, and financial transactions PayPal - Integrate PayPal commerce capabilities, payment processing, transaction management Square - Use an agent to build on Square APIs. Payments, inventory, orders, and more
Need a specific integration? Find hundreds more MCP servers on GitHub, or build your own using the MCP SDK.

​
Installing MCP servers

MCP servers can be configured in two ways: using the interactive gammacode mcp add command or by editing your gammacode.jsonc configuration file directly.

​
Interactive installation

Use the interactive command to add MCP servers with a guided setup: 
gammacode mcp add
This will prompt you through an interactive flow: 
┌  Add MCP server
│
◇  Enter MCP server name
│  asana
│
◇  Select MCP server type
│  Remote
│
◇  Enter MCP server URL
│  https://mcp.asana.com/sse
MCP server types:
  • Remote: Connect to hosted MCP services via HTTP or SSE URLs
  • Local: Run MCP servers as local processes on your machine

​
Configuration file setup

You can also configure MCP servers directly in your gammacode.json file: 
{
  "mcp": {
    "asana": {
      "type": "remote",
      "url": "https://mcp.asana.com/sse",
      "enabled": true
    },
    "notion": {
      "type": "remote", 
      "url": "https://mcp.notion.com/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    },
    "local-server": {
      "type": "local",
      "command": ["npx", "-y", "@modelcontextprotocol/server-everything"],
      "enabled": true,
      "environment": {
        "API_KEY": "your-api-key"
      }
    }
  }
}

​
Local server configuration

For local MCP servers, you’ll need to specify the command and any environment variables: 
{
  "mcp": {
    "airtable": {
      "type": "local",
      "command": ["npx", "-y", "airtable-mcp-server"],
      "environment": {
        "AIRTABLE_API_KEY": "YOUR_API_KEY"
      },
      "enabled": true
    },
    "database": {
      "type": "local", 
      "command": ["node", "./scripts/database-mcp-server.js"],
      "environment": {
        "DATABASE_URL": "postgresql://user:pass@localhost:5432/db"
      },
      "enabled": true
    }
  }
}

​
Managing your servers

Once configured, you can manage your MCP servers: 
# List all configured servers
gammacode mcp list

# Remove a server (interactive)
gammacode mcp remove

# (within Gammacode) Check server status and authenticate
/mcp
You can also manage servers by editing your gammacode.json file directly to:
  • Add new servers
  • Modify existing server configurations
  • Enable/disable servers by setting "enabled": true/false
  • Update URLs, commands, or environment variables
Tips:
  • Configure MCP server startup timeout using the MCP_TIMEOUT environment variable (e.g., MCP_TIMEOUT=10000 gammacode sets a 10-second timeout)
  • Gammacode will display a warning when MCP tool output exceeds 10,000 tokens. To increase this limit, set the MAX_MCP_OUTPUT_TOKENS environment variable (e.g., MAX_MCP_OUTPUT_TOKENS=50000)
  • Use /mcp within Gammacode to authenticate with remote servers that require OAuth 2.0 authentication
  • Changes to gammacode.json require restarting Gammacode to take effect

​
Configuration locations

MCP servers can be configured in different locations depending on your needs:

​
Global configuration

  • Location: ~/.gammacode/gammacode.json
  • Scope: Available across all projects

​
Project configuration

  • Location: .gammacode/gammacode.json (in your project root)
  • Scope: Available only in current project
  • Priority: Project settings override global settings

​
Environment variable expansion

Gammacode supports environment variable expansion in configuration files, allowing you to keep sensitive data secure while sharing configurations. Supported syntax:
  • ${VAR} - Expands to the value of environment variable VAR
  • ${VAR:-default} - Expands to VAR if set, otherwise uses default
Example with environment variables: 
{
  "mcp": {
    "api-server": {
      "type": "remote",
      "url": "${API_BASE_URL:-https://api.example.com}/mcp",
      "headers": {
        "Authorization": "Bearer ${API_KEY}"
      }
    },
    "database": {
      "type": "local",
      "command": ["node", "server.js"],
      "environment": {
        "DATABASE_URL": "${DATABASE_URL}",
        "DB_PASSWORD": "${DB_PASSWORD}"
      }
    }
  }
}
This allows you to:
  • Keep API keys and sensitive data in environment variables
  • Share configuration files safely in version control
  • Use different configurations for development/staging/production

​
Practical examples

​
Example: Monitor errors with Sentry

# 1. Add the Sentry MCP server
gammacode mcp add
# Follow prompts: name=sentry, type=Remote, url=https://mcp.sentry.dev/mcp

# 2. Use /mcp to authenticate with your Sentry account
> /mcp

# 3. Debug production issues
> "What are the most common errors in the last 24 hours?"
> "Show me the stack trace for error ID abc123"
> "Which deployment introduced these new errors?"

​
Example: Connect to Notion for documentation

# 1. Add the Notion MCP server
gammacode mcp add
# Follow prompts: name=notion, type=Remote, url=https://mcp.notion.com/mcp

# 2. In Gammacode, authenticate if needed
> /mcp
# Select "Authenticate" for Notion

# 3. Now you can ask Gammacode to work with Notion
> "Show me all pages in the Engineering workspace"
> "Create a new page for the API documentation"
> "Update the project roadmap with this week's progress"

​
Example: Add a local database server

For local servers, you can configure them in your gammacode.json file: 
{
  "mcp": {
    "database": {
      "type": "local",
      "command": ["npx", "-y", "@bytebase/dbhub"],
      "environment": {
        "DATABASE_URL": "postgresql://readonly:pass@localhost:5432/analytics"
      },
      "enabled": true
    }
  }
}
Then query your database naturally: 
> "What's our total revenue this month?"
> "Show me the schema for the orders table"
> "Find customers who haven't made a purchase in 90 days"

​
Authenticate with remote MCP servers

Many cloud-based MCP servers require authentication. Gammacode supports OAuth 2.0 for secure connections.
1

Add the server that requires authentication

For example:
gammacode mcp add --transport http sentry https://mcp.sentry.dev/mcp
2

Use the /mcp command within Gammacode

In Gammacode, use the command:
> /mcp
Then follow the steps in your browser to login.
Tips:
  • Authentication tokens are stored securely and refreshed automatically
  • Use “Clear authentication” in the /mcp menu to revoke access
  • If your browser doesn’t open automatically, copy the provided URL
  • OAuth authentication works with HTTP servers

​
Advanced MCP server examples

​
API server with authentication

{
  "mcp": {
    "weather-api": {
      "type": "remote",
      "url": "https://api.weather.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN",
        "X-API-Version": "v2"
      },
      "enabled": true
    }
  }
}

​
Local development server

{
  "mcp": {
    "local-dev": {
      "type": "local",
      "command": ["python", "./scripts/dev-mcp-server.py"],
      "environment": {
        "DEBUG": "true",
        "PORT": "8080",
        "CONFIG_PATH": "./config/dev.json"
      },
      "enabled": true
    }
  }
}

​
Use MCP resources

MCP servers can expose resources that you can reference using @ mentions, similar to how you reference files.

​
Reference MCP resources

1

List available resources

Type @ in your prompt to see available resources from all connected MCP servers. Resources appear alongside files in the autocomplete menu.
2

Reference a specific resource

Use the format @server:protocol://resource/path to reference a resource:
> Can you analyze @github:issue://123 and suggest a fix?

> Please review the API documentation at @docs:file://api/authentication
3

Multiple resource references

You can reference multiple resources in a single prompt:
> Compare @postgres:schema://users with @docs:file://database/user-model
Tips:
  • Resources are automatically fetched and included as attachments when referenced
  • Resource paths are fuzzy-searchable in the @ mention autocomplete
  • Gammacode automatically provides tools to list and read MCP resources when servers support them
  • Resources can contain any type of content that the MCP server provides (text, JSON, structured data, etc.)

​
Use MCP prompts as slash commands

MCP servers can expose prompts that become available as slash commands in Gammacode.

​
Execute MCP prompts

1

Discover available prompts

Type / to see all available commands, including those from MCP servers. MCP prompts appear with the format /mcp__servername__promptname.
2

Execute a prompt without arguments

> /mcp__github__list_prs
3

Execute a prompt with arguments

Many prompts accept arguments. Pass them space-separated after the command:
> /mcp__github__pr_review 456

> /mcp__jira__create_issue "Bug in login flow" high
Tips:
  • MCP prompts are dynamically discovered from connected servers
  • Arguments are parsed based on the prompt’s defined parameters
  • Prompt results are injected directly into the conversation
  • Server and prompt names are normalized (spaces become underscores)

​
Use Gammacode as an MCP server

You can use Gammacode itself as an MCP server that other applications can connect to: 
# Start Gammacode as a stdio MCP server
gammacode mcp serve
You can use this in other MCP clients by adding this configuration: 
{
  "mcpServers": {
    "gammacode": {
      "type": "stdio",
      "command": "gammacode",
      "args": ["mcp", "serve"],
      "env": {}
    }
  }
}
Tips:
  • The server provides access to Gammacode’s tools like View, Edit, LS, etc.
  • In other MCP clients, try asking them to read files in a directory, make edits, and more.
  • Note that this MCP server is simply exposing Gammacode’s tools to your MCP client, so your own client is responsible for implementing user confirmation for individual tool calls.

​
MCP output limits and warnings

When MCP tools produce large outputs, Gammacode helps manage the token usage to prevent overwhelming your conversation context:
  • Output warning threshold: Gammacode displays a warning when any MCP tool output exceeds 10,000 tokens
  • Configurable limit: You can adjust the maximum allowed MCP output tokens using the MAX_MCP_OUTPUT_TOKENS environment variable
  • Default limit: The default maximum is 25,000 tokens
To increase the limit for tools that produce large outputs: 
# Set a higher limit for MCP tool outputs
export MAX_MCP_OUTPUT_TOKENS=50000
gammacode
This is particularly useful when working with MCP servers that:
  • Query large datasets or databases
  • Generate detailed reports or documentation
  • Process extensive log files or debugging information
If you frequently encounter output warnings with specific MCP servers, consider increasing the limit or configuring the server to paginate or filter its responses.

​
Next steps

Agents

Learn how to configure agents with specific MCP tools for specialized workflows

Permissions

Control access to MCP tools with granular permission settings

Custom Commands

Create custom commands that leverage MCP tools for repetitive tasks

Headless Mode

Use MCP tools programmatically in automated workflows
⌘I