MCP SaaS Bridge
A unified MCP server that connects AI agents to Jira, Notion, and GitHub, enabling search, create, and update actions across these services.
README
MCP SaaS Bridge
A single MCP server that connects your AI agent to Jira, Notion, and GitHub — in one unified interface. One config, one deployment, every tool your team uses.
What it does
Your AI agent (Claude Desktop, Cursor, OpenClaw) can now:
| Action | Jira | Notion | GitHub |
|---|---|---|---|
| Search / browse | Search issues by JQL | Search pages by keyword | List open PRs |
| Create | Create tickets with type & priority | Create pages in any workspace | Create issues with labels |
| Update | Transition status, add comments | Append content to pages | — |
Quick start
1. Set environment variables
cp .env.example .env
# Add at least one tool credentials:
# JIRA_URL=https://yourcompany.atlassian.net
# JIRA_EMAIL=you@company.com
# JIRA_API_TOKEN=your-token
# NOTION_API_KEY=secret_xxxxx
# GITHUB_TOKEN=ghp_xxxxx
2. Run
# Docker
docker compose up
# Or standalone
npm install && npm run build && npm start
3. Connect to Claude Desktop
{
"mcpServers": {
"saas-bridge": {
"command": "node",
"args": ["/absolute/path/to/mcp-saas-bridge/dist/index.js"],
"env": {
"JIRA_URL": "https://yourcompany.atlassian.net",
"JIRA_EMAIL": "you@company.com",
"JIRA_API_TOKEN": "your-token",
"NOTION_API_KEY": "secret_xxxxx",
"GITHUB_TOKEN": "ghp_xxxxx"
}
}
}
}
Configure only the tools you use. Unused services can stay commented out.
Example conversations
Your PM: "Summarize my open Jira tickets and write a project update to Notion" Claude:
- Calls
jira_search_issues→ gets 12 open tickets - Calls
notion_create_page→ writes a summary to your project docs
Your dev: "Show me open PRs in my repo and create a Jira ticket for any that need review" Claude:
- Calls
github_list_prs→ finds 3 open PRs - Calls
jira_create_issue→ creates review tasks in Jira
Security
- All tokens stay local — no data leaves your infrastructure
- Uses official SDKs for each service (no unofficial wrappers)
- OAuth2 and token-based auth only — no password storage
- Supports environment variable injection from Docker secrets or vaults
Tech stack
- MCP SDK — Model Context Protocol
- Node.js / TypeScript
- @notionhq/client — Notion SDK
- @octokit/rest — GitHub SDK
- Docker Compose for deployment
Built on the Model Context Protocol.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.