assessorai-dados
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | Yes | The PostgreSQL connection string used by the application. | |
| PUBLIC_API_KEY_HASHES | No | Optional environment variable containing SHA-256 hashes of API keys allowed to access public endpoints. Keys are sent via X-API-Key. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_propositionsC | Search propositions using identifiers, text, semantic similarity and filters. |
| get_propositionA | Get canonical metadata and provenance for one proposition UUID. |
| read_proposition_textB | Read a bounded page of a proposition's full text. |
| find_related_propositionsB | Find propositions related by embeddings or Portuguese full-text similarity. |
| list_sourcesA | List data sources, jurisdictions, licenses and redistribution status. |
| get_dataset_releaseC | Get a release manifest and its coverage metadata. |
| get_dataset_downloadC | Get a public GitHub Release URL for a named dataset asset. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| dataset_catalog | Catalog of published dataset releases. |
TDQS
Scored across 7 tools
Each tool targets a distinct task: metadata lookup, source enumeration, search, text paging, related-item discovery, release manifest retrieval, and download URL resolution. Even the release/download pair is clearly separated by manifest metadata versus asset URL.
All tool names follow a consistent snake_case verb_noun pattern (get, list, search, read, find). The naming style is uniform and predictable across the entire set.
Seven tools is well-scoped for a read-only legislative data API. Each tool covers a meaningful part of the workflow without redundancy or bloat.
The tool surface covers the full read-only lifecycle: discovery via search, metadata retrieval, full-text access, related-proposition exploration, and dataset distribution. Dependencies between tools are coherent, with no obvious dead ends for common workflows.