Igniral MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IGNIRAL_API_URL | No | API URL (default: https://api.igniral.io) | https://api.igniral.io |
| IGNIRAL_AUTH_URL | No | Auth server URL (default: https://auth.igniral.com) | https://auth.igniral.com |
| IGNIRAL_CLIENT_ID | Yes | Agent API Key client ID (from Dashboard) | |
| IGNIRAL_AI_API_URL | No | AI API URL (default: https://ai.igniral.com) | https://ai.igniral.com |
| IGNIRAL_CLIENT_SECRET | Yes | Agent API Key client secret (shown once at creation) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| igniral_generate_schema_from_promptA | Generates a complete application from a natural language description. This tool creates the application, ALL endpoints with their JSON schemas, roles, and permissions automatically. Use this when the user gives a general or ambiguous instruction like "build me a gym management app" or "create an API for a restaurant". You do NOT need to call igniral_create_application or igniral_create_dynamic_endpoint after this — everything is created automatically. This may take 30-90 seconds to complete. Returns the applicationId and a summary of what was created. |
| igniral_create_applicationA | Creates an empty application shell (without endpoints). Use this when the user wants to manually build an application step by step, providing a specific name, description, and settings. After creating the application, use igniral_create_dynamic_endpoint to add API endpoints one by one. Returns the applicationId needed for creating endpoints. Do NOT use this after igniral_generate_schema_from_prompt — that tool already creates the application automatically. |
| igniral_create_dynamic_endpointA | Creates a dynamic API endpoint within an existing application. Requires an applicationId from a previous igniral_create_application call. Use this iteratively to add all needed endpoints to the application. Each endpoint defines its data schema (JSON Schema format), HTTP methods, visibility (PUBLIC/PRIVATE), and security policy. Security policies:
|
| igniral_list_applicationsA | Lists all applications owned by the current user. Use this to check what applications already exist before creating new ones, or to get the applicationId of an existing application. Takes no parameters — the user is identified by the configured service token. |
| igniral_update_dynamic_endpointA | Updates a dynamic API endpoint within an existing application. Requires an endpointId from a previous list_applications call. Use this to modify the schema or configuration of an already existing endpoint. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct action: creating an empty app, adding endpoints, generating full app from prompt, listing apps, and updating endpoints. The descriptions explicitly warn against using create_application after generate_schema_from_prompt, reducing ambiguity.
All tools follow a consistent verb_noun pattern with the prefix 'igniral_': create_application, create_dynamic_endpoint, generate_schema_from_prompt, list_applications, update_dynamic_endpoint. Minor length variation does not break consistency.
5 tools is well-scoped for the domain of application and dynamic endpoint management. It covers creation (two modes), listing, and updating without being overly numerous or sparse.
The set covers creation, listing, and update operations but lacks any delete functionality (e.g., delete endpoint or delete application). This is a notable gap that could hinder agent workflows requiring removal.