Insforge MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | Yes | Your InsForge API key | |
| API_BASE_URL | No | Your InsForge instance URL | http://localhost:7130 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch-docsA | Fetch Insforge documentation. Use "instructions" for essential backend setup (MANDATORY FIRST), or select specific SDK docs for database, auth, storage, functions, or AI integration. |
| get-anon-keyA | Generate an anonymous JWT token that never expires. Requires admin API key. Use this for client-side applications that need public access. |
| get-table-schemaB | Returns the detailed schema(including RLS, indexes, constraints, etc.) of a specific table |
| get-backend-metadataC | Index all backend metadata |
| run-raw-sqlA | Execute raw SQL query with optional parameters. Admin access required. Use with caution as it can modify data directly. |
| download-templateA | CRITICAL: MANDATORY FIRST STEP for all new InsForge projects. Download pre-configured starter template to a temporary directory. After download, you MUST copy files to current directory using the provided command. |
| bulk-upsertC | Bulk insert or update data from CSV or JSON file. Supports upsert operations with a unique key. |
| create-bucketC | Create new storage bucket |
| list-bucketsB | Lists all storage buckets |
| delete-bucketC | Deletes a storage bucket |
| create-functionC | Create a new edge function that runs in Deno runtime. The code must be written to a file first for version control |
| get-functionC | Get details of a specific edge function including its code |
| update-functionC | Update an existing edge function code or metadata |
| delete-functionC | Delete an edge function permanently |
| get-container-logsB | Get latest logs from a specific container/service. Use this to help debug problems with your app. |
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 15 tools
Most tools have distinct purposes targeting specific resources like buckets, functions, or SQL operations, but some overlap exists: 'create-function' and 'update-function' are clearly related but distinct, while 'get-backend-metadata' and 'get-table-schema' could be confused as both retrieve metadata, though their descriptions clarify the scope. Overall, the descriptions help differentiate tools effectively.
The naming follows a consistent verb-noun pattern with hyphens (e.g., 'create-bucket', 'delete-function', 'get-table-schema'), which is predictable and readable. There are minor deviations: 'bulk-upsert' uses a compound verb and 'download-template' and 'fetch-docs' have slightly different structures, but these do not significantly hinder clarity.
With 15 tools, the count is well-scoped for a backend management server covering storage, functions, SQL, documentation, and setup. Each tool serves a clear purpose, such as CRUD operations for buckets and functions, and there are no redundant or trivial tools, making the set appropriately sized for the domain.
The tool set provides good coverage for backend operations, including CRUD for buckets and functions, SQL execution, logging, and documentation. Minor gaps exist: there is no tool for updating bucket metadata or listing functions, which could limit lifecycle management, but core workflows like setup, deployment, and debugging are well-supported.