About The Graph Token API MCP
The Graph Token API MCP is an MCP server for accessing The Graph Token API. The README describes Token API access and SQL queries, but does not list specific data categories.
Key features
- 01Connects to The Graph Token API
- 02Serves MCP over HTTP
- 03Supports SSE and HTTP streaming
- 04Configurable port and database host
Use cases
- 01Access The Graph Token API from an MCP client
- 02Connect to a local MCP server over SSE
- 03Connect to the server using HTTP streaming
MCP support
It connects The Graph Token API to MCP so MCP clients can query structured blockchain data; the server supports SSE and HTTP streaming.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
4Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEmcp-token-api
Run with Bun:
$ bun run index.ts
Server will be running on http://localhost:8080/sse for SSE and http://localhost:8080/stream for HTTP streaming.
Usage: mcp-token-api [options]
MCP server for The Graph Token API
Options:
-V, --version output the version number
-p, --port <number> HTTP port on which to attach the MCP SSE server (default: "8080", env: PORT)
--url <string> Database HTTP hostname (default: "http://localhost:8123", env: URL)
--database <string> The database to use inside ClickHouse (default: "default", env: DATABASE)
--username <string> Database user for API (default: "default", env: USERNAME)
--password <string> Password associated with the specified API username (default: "", env: PASSWORD)
--pretty-logging <boolean> Enable pretty logging (default JSON) (choices: "true", "false", default: false, env: PRETTY_LOGGING)
-v, --verbose <boolean> Enable verbose logging (choices: "true", "false", default: false, env: VERBOSE)
-h, --help display help for command
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.