Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a searchable Graphlit project.
Graphlit MCP server exists for a simple reason — assistants are far more useful when they can act on Graphlit directly instead of describing what you should do. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a searchable Graphlit project.
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. This document outlines the setup process and provides a basic example of using the client.
The server ships on npm as graphlit-mcp-server, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Once Graphlit is connected, these are the calls the assistant has available:
Retrieval — The Retrieval tool exposed by this serverExtraction — The Extraction tool exposed by this serverPublishing — The Publishing tool exposed by this serverIngestion — The Ingestion tool exposed by this serverNotifications — The Notifications tool exposed by this serverOperations — The Operations tool exposed by this serverEnumerations — The Enumerations tool exposed by this serverYou will need 8 environment variables: GRAPHLIT_ORGANIZATION_ID, GRAPHLIT_ENVIRONMENT_ID, GRAPHLIT_JWT_SECRET, SLACK_BOT_TOKEN, DISCORD_BOT_TOKEN, TWITTER_TOKEN, GOOGLE_EMAIL_REFRESH_TOKEN, GOOGLE_EMAIL_CLIENT_ID. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Before you begin, ensure you have the following: - Node.js installed on your system (recommended version 18.x or higher). - An active account on the Graphlit Platform with access to the API settings dashboard.
This sits in the team communication group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Graphlit's toolset — Retrieval, Extraction, Publishing and 4 more — is a fair guide to whether it matches your workflow.
This entry was verified against Graphlit's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Retrieval | The Retrieval tool exposed by this server. |
| Extraction | The Extraction tool exposed by this server. |
| Publishing | The Publishing tool exposed by this server. |
| Ingestion | The Ingestion tool exposed by this server. |
| Notifications | The Notifications tool exposed by this server. |
| Operations | The Operations tool exposed by this server. |
| Enumerations | The Enumerations tool exposed by this server. |
{
"mcpServers": {
"graphlit": {
"command": "npx",
"args": ["-y", "graphlit-mcp-server"],
"env": {
"GRAPHLIT_ORGANIZATION_ID": "your-value",
"GRAPHLIT_ENVIRONMENT_ID": "your-value",
"GRAPHLIT_JWT_SECRET": "your-value",
"SLACK_BOT_TOKEN": "your-value",
"DISCORD_BOT_TOKEN": "your-value",
"TWITTER_TOKEN": "your-value",
"GOOGLE_EMAIL_REFRESH_TOKEN": "your-value",
"GOOGLE_EMAIL_CLIENT_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Before you begin, ensure you have the following: - Node.js installed on your system (recommended version 18.x or higher). - An active account on the Graphlit Platform with access to the API settings dashboard.
| Variable | Description | Required |
|---|---|---|
| GRAPHLIT_ORGANIZATION_ID | Configuration value read at startup. | Optional |
| GRAPHLIT_ENVIRONMENT_ID | Configuration value read at startup. | Optional |
| GRAPHLIT_JWT_SECRET | Credential the server authenticates with. | Yes |
| SLACK_BOT_TOKEN | Credential the server authenticates with. | Yes |
| DISCORD_BOT_TOKEN | Credential the server authenticates with. | Yes |
| TWITTER_TOKEN | Credential the server authenticates with. | Yes |
| GOOGLE_EMAIL_REFRESH_TOKEN | Credential the server authenticates with. | Yes |
| GOOGLE_EMAIL_CLIENT_ID | Configuration value read at startup. | Optional |
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Inbox intelligence — search, read, draft and send Gmail through your assistant with OAuth auto-setup.
Read and write Jira, Confluence, Bitbucket, JSM and Compass from your AI client — with your own permissions.
Read and send Telegram messages through your assistant — chats, channels and history via the client API.
MCP server enabling room-based messaging between multiple agents
AI-powered access to Attio CRM. Manage contacts, companies, deals, tasks, and notes. Search records, update pipelines, and automate workflows for