Gadget MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GADGET_APP | Yes | App slug, e.g. my-app | |
| GADGET_API_KEY | Yes | Production API key | |
| GADGET_ENVIRONMENT | No | The environment to connect to (production or development) | production |
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 | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| introspect_modelA | List all fields and their types for a Gadget model. Run this first when you're unsure what fields exist on a model. |
| list_modelsA | List all models (types) available in this Gadget app via GraphQL introspection. |
| query_recordsA | Query records from any Gadget model. Supports filtering, sorting, pagination cursors, and field selection (all scalar fields by default). Use introspect_filters to see valid filter shapes. |
| count_recordsA | Return the total number of records for a Gadget model, with optional filtering. |
| get_recordC | Get a single Gadget record by ID. Specify the model name, record ID, and fields to return. |
| introspect_filtersA | Show all available filter fields and their types for a Gadget model. Use this to construct valid filter arguments for query_records and count_records. |
| introspect_actionsA | List all actions (mutations) available in this Gadget app, including their arguments. Use this to find action names and argument shapes for run_action, create_record, and update_record. |
| get_schema_overviewA | Return all models with their fields and types in a single call. Use this for a broad understanding of the app schema before diving into specific models. |
| report_bugA | Create a pre-filled GitHub bug report link for this MCP server (gadget-mcp itself, not the user's Gadget app). Use when a gadget-mcp tool misbehaves or the user asks to report a bug. Returns a link for the user to review and submit — nothing is posted automatically. Do not include API keys or customer data. |
| run_graphqlA | Run an arbitrary read-only GraphQL query against the Gadget app. Use this for complex queries with nested relations or custom filtering that query_records can't express. |
| export_recordsA | Export many records (beyond query_records' 50) to a CSV or JSON file on this machine for analysis or sharing. Pages through automatically. Returns the file path, row count, columns and a short preview. Redaction settings apply. |
| group_countA | Count records grouped by a field's value, e.g. orders by financialStatus or products by vendor. Exact for enum and boolean fields; other fields are counted by scanning (up to max_records) and say whether the result is exact. |
| read_logsA | Read recent logs from the Gadget app (via the ggt CLI) to debug errors, failed actions or webhooks. Defaults to the last 15 minutes at info level. Needs a one-time |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| explore_app | Get a plain-English overview of the app's models, how they relate, and how much data each holds. |
| debug_record | Investigate why a specific record looks wrong or an action on it failed. |
| audit_errors | Find and group recent errors in the app logs, with likely causes. |
| data_health | Check a model for missing values, odd statuses and other data-quality issues. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Most tools target distinct operations (query_records vs run_graphql vs export_records vs group_count are clearly differentiated), but there is a cluster of five overlapping introspection tools (list_models, get_schema_overview, introspect_model, introspect_filters, introspect_actions) where get_schema_overview largely subsumes list_models and introspect_model. Descriptions do clarify the layering, so misselection is possible but avoidable.
Every tool follows a clean snake_case verb_noun pattern (count_records, introspect_model, list_models, get_record, run_graphql, query_records, export_records, group_count, read_logs, report_bug). No camelCase or style mixing; conventions are fully predictable.
13 tools is well-scoped for a data-access/introspection server, and each tool covers a distinct capability (query, count, group, export, schema introspection, logs, bug reporting). Nothing feels redundant or padded.
The surface covers read, count, group, export, and introspection well, but the introspect_actions description explicitly points users toward run_action, create_record, and update_record — none of which exist in the tool set — creating a dead end for mutations. There is also no delete operation, so the lifecycle is notably incomplete for the referenced domain.