Skip to main content
Glama
UseGrant MCP Server

UseGrant MCP Server

Official
by usegranthq

UseGrant MCP Server

This is a Model Context Protocol (MCP) server for interacting with the UseGrant API. It provides a set of tools for managing providers, clients, tenants, and access tokens through the UseGrant platform.

Tools

The tools are generated from the UseGrant OpenAPI spec when the server starts, one tool per API operation, so new API operations are available without updating the server.

Tools are named after the operation, for example:

  • providers_list: List Providers

  • providers_clients_create: Create Client

  • providers_domains_verify: Verify Domain

  • tenants_providers_policies_create: Create Tenant Provider Policy

  • tenants_tokens_validate: Validate Token

Read-only operations are marked with readOnlyHint and delete operations with destructiveHint, so MCP clients can ask for confirmation before changing anything.

Related MCP server: MCP Boilerplate

Requirements

  • Node.js 22.19 or higher

  • Network access to sdk.usegrant.dev, the OpenAPI spec is loaded on start

  • A valid UseGrant API key. Refer here for more details.

Using with Claude desktop

Add the following config to your claude_desktop_config file:

{
  "mcpServers": {
    "usegrant": {
      "command": "npx",
      "args": ["-y", "@usegrant/mcp"],
      "env": {
        "USEGRANT_API_KEY": "your_api_key_here"
      }
    }
  }
}

Testing

To test the MCP server, we can use mcp inspector.

Copy the .env.example file to .env and set the USEGRANT_API_KEY environment variable.

npx @modelcontextprotocol/inspector -e USEGRANT_API_KEY=$USEGRANT_API_KEY npx tsx src/index.ts

To watch and build the project:

npm run dev

License

This project is licensed under the MIT License. See the LICENSE file for details.

Available Tools

27 tools
providers_clients_createCreate ClientD

Create Client

Inputs: name (required), audience (required), providerId (required).

providers_clients_deleteDelete ClientC
DestructiveIdempotent

Delete Client

Inputs: clientId (required), providerId (required).

providers_clients_getGet ClientC
Read-onlyIdempotent

Get Client

Inputs: clientId (required), providerId (required).

providers_clients_listList ClientsC
Read-onlyIdempotent

List Clients

Inputs: providerId (required).

providers_clients_tokens_createCreate Access TokenD

Create Access Token

Inputs: clientId (required), providerId (required), expiresIn, useJwtType, +2 more.

providers_createCreate ProviderD

Create Provider

Inputs: name (required), description (required).

providers_deleteDelete ProviderC
DestructiveIdempotent

Delete Provider

Inputs: id (required).

providers_domains_addAdd Domain to ProviderC

Add Domain to Provider

Inputs: domain (required), providerId (required).

providers_domains_deleteDelete DomainC
DestructiveIdempotent

Delete Domain

Inputs: domainId (required), providerId (required).

providers_domains_getGet DomainD
Read-onlyIdempotent

Get Domain

Inputs: domainId (required), providerId (required).

providers_domains_listList DomainsC
Read-onlyIdempotent

List Domains

Inputs: providerId (required).

providers_domains_verifyVerify DomainC

Verify Domain

Inputs: domainId (required), providerId (required).

providers_getGet ProviderC
Read-onlyIdempotent

Get Provider

Inputs: id (required).

providers_listList ProvidersC
Read-onlyIdempotent

List Providers

Inputs: no named parameters.

tenants_createCreate TenantD

Create Tenant

Inputs: name (required), description (required).

tenants_deleteDelete TenantD
DestructiveIdempotent

Delete Tenant

Inputs: id (required).

tenants_getGet TenantC
Read-onlyIdempotent

Get Tenant

Inputs: id (required).

tenants_listList TenantsC
Read-onlyIdempotent

List Tenants

Inputs: no named parameters.

tenants_providers_createCreate Tenant ProviderD

Create Tenant Provider

Inputs: url (required), audience (required), tenantId (required), fingerprints (required), +1 more.

tenants_providers_deleteDelete Tenant ProviderC
DestructiveIdempotent

Delete Tenant Provider

Inputs: tenantId (required), tenantProviderId (required).

tenants_providers_getGet Tenant ProviderC
Read-onlyIdempotent

Get Tenant Provider

Inputs: tenantId (required), tenantProviderId (required).

tenants_providers_listList Tenant ProvidersC
Read-onlyIdempotent

List Tenant Providers

Inputs: tenantId (required).

tenants_providers_policies_createCreate Tenant Provider PolicyD

Create Tenant Provider Policy

Inputs: name (required), audience (required), tenantId (required), description (required), +2 more.

tenants_providers_policies_deleteDelete Tenant Provider PolicyC
DestructiveIdempotent

Delete Tenant Provider Policy

Inputs: policyId (required), tenantId (required), tenantProviderId (required).

tenants_providers_policies_getGet Tenant Provider PolicyC
Read-onlyIdempotent

Get Tenant Provider Policy

Inputs: policyId (required), tenantId (required), tenantProviderId (required).

tenants_providers_policies_listList Tenant Provider PoliciesC
Read-onlyIdempotent

List Tenant Provider Policies

Inputs: tenantId (required), tenantProviderId (required).

tenants_tokens_validateValidate TokenD

Validate Token

Inputs: token (required), tenantId (required), tenantProviderPolicyId (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.4/5.0

    Scored across 27 tools

    Disambiguation4/5

    The hierarchical resource paths make most tools clearly distinct, especially across providers, clients, domains, tenants, tenant providers, and policies. Some boundaries are still easy to confuse, such as provider clients' token creation versus tenant token validation, but descriptions provide enough context.

    Naming Consistency5/5

    Tool names consistently use snake_case with a hierarchical resource path followed by a verb, such as providers_clients_list and tenants_providers_policies_create. Domain-specific verbs like add and verify are used appropriately without breaking the overall pattern.

    Tool Count3/5

    The 27-tool surface is heavy for a single MCP server, but it is structured around CRUD operations for several nested resource types rather than arbitrary one-off tools. It is borderline appropriate for a multi-tenant provider/client/domain/policy domain, though still larger than ideal.

    Completeness3/5

    The server covers many core list/get/create/delete operations across providers, clients, domains, tenants, tenant providers, and policies. However, update operations are largely absent, and token lifecycle coverage is incomplete because there is token creation and validation but no token listing, revocation, or deletion.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers