An MCP server for managing AI agent authorization with scoped tokens, grants, revocation, audit trails, and principal sessions. It exposes tools for registering agents, creating authorization requests, exchanging and verifying tokens, and managing grants and audits.
From the registry: OAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.
$ npm install -g @grantex/mcpPlease install the `grantex` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install the Grantex MCP package globally** — Install the MCP server CLI so the `grantex-mcp` command is available. Run: `npm install -g @grantex/mcp`
- **Create a Grantex API key** — Get a Grantex API key from the Grantex dashboard. This is required for the server to authenticate to the Grantex API. (https://grantex.dev/dashboard/signup)
Canonical MCP server config (stdio transport):
- command: `grantex-mcp`
- args: []
- required environment variables:
- `GRANTEX_API_KEY`: Your Grantex API key. (example: `<your-api-key>`)
- optional environment variables:
- `GRANTEX_BASE_URL`: Override the Grantex API base URL. (example: `<your-grantex-base-url>`)
Note: README shows stdio configuration for multiple MCP clients using the same canonical command. Default API base URL is managed by the server; only set GRANTEX_BASE_URL when overriding it.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GRANTEX_API_KEYrequiredYour Grantex API keyAI-powered threat hunting and incident response MCP server for Elasticsearch/OpenSearch