Spice MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DUNE_API_KEY | Yes | Your Dune Analytics API key (required) | |
| SPICE_MCP_SKIP_DOTENV | No | Set to 1 to skip loading .env file during tests/CI | 0 |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| dune_query_infoC | Fetch Dune query metadata (name, parameters, tags, SQL). |
| dune_queryC | Execute Dune queries and return agent-optimized preview. |
| dune_health_checkA | Validate Dune API key presence and logging setup. |
| dune_discoverA | Unified tool to discover tables/models from Dune API and/or Spellbook repository. Search by keyword(s) or list tables in a schema. |
| dune_describe_tableC | Describe columns for a schema.table on Dune. |
| dune_query_createB | Create a new saved Dune query (name + SQL). Requires SPICE_DUNE_ALLOW_SAVES=true. |
| dune_query_updateC | Update fields of a saved Dune query (name/SQL/description/tags/parameters). Requires SPICE_DUNE_ALLOW_SAVES=true. |
| dune_query_forkC | Fork an existing saved Dune query. Requires SPICE_DUNE_ALLOW_SAVES=true. |
| dune_query_archiveC | Archive a saved Dune query. |
| dune_query_unarchiveC | Unarchive a saved Dune query. |
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 10 tools
Each tool has a clear, distinct purpose: describe table columns, discover tables/models, health check, execute query, and manage saved queries (create, info, update, archive, unarchive, fork). No overlap.
All tools follow the 'dune_' prefix with a verb_noun pattern (e.g., dune_describe_table, dune_query_create). The naming is uniform and predictable.
10 tools is well-scoped for a Dune analytics server, covering core table inspection, query execution, and saved query lifecycle without unnecessary bloat.
Covers essential operations: describing/discovering tables, health, query execution, and saved query CRUD (except delete). Missing a list saved queries tool and explicit deletion, but core workflows are supported.