Pluggy MCP Starter
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HTTP_TOKEN | No | Long token for HTTP server mode | |
| PLUGGY_ITEM_IDS | Yes | Comma-separated list of Pluggy item IDs to query | |
| PLUGGY_CLIENT_ID | Yes | Your Pluggy client ID | |
| PLUGGY_CLIENT_SECRET | Yes | Your Pluggy client secret |
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 |
|---|---|
| pluggy_schemaB | SQL fields, semantics, and transaction limitations. Does not access secrets. |
| pluggy_queryA | Read-only SQLite SELECT over accounts and transactions for the requested UTC period. accounts includes every account returned by every configured Pluggy connection, including accounts without transactions. Reuses collection in memory for 15 minutes and returns coverage metadata. Call pluggy_schema before computing totals. |
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 2 tools
The two tools have clearly distinct roles: pluggy_schema provides metadata and semantics, while pluggy_query executes read-only SQL. The query description explicitly directs agents to call the schema tool first, reducing any risk of misselection.
Both tools follow the same pluggy_ prefix and snake_case convention. The names are predictable and readable.
Only two tools are provided, which is borderline thin for a server with a defined domain. While the starter scope makes this acceptable, it is below the typical well-scoped range of 3-15 tools.
For a read-only query server, schema discovery plus SQL SELECT covers the core lifecycle. Minor convenience gaps exist, such as direct connection/account listing, but raw SQL can work around them.