pgroonga-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PGROONGA_MAX_ROWS | No | Maximum search row limit | 100 |
| PGROONGA_LOG_LEVEL | No | Log level: debug, info, warn, or error | info |
| PGROONGA_TRANSPORT | No | Only stdio is currently supported | stdio |
| PGROONGA_DATABASE_URL | Yes | PostgreSQL connection URL (required) | |
| PGROONGA_MAX_VARIANTS | No | Variant lookup limit | 500 |
| PGROONGA_DEFAULT_LIMIT | No | Default search row limit | 20 |
| PGROONGA_ALLOWED_TABLES | No | Comma-separated table allowlist | |
| PGROONGA_MAX_TEXT_BYTES | No | Per-string result limit | 131072 |
| PGROONGA_ALLOWED_SCHEMAS | No | Comma-separated schema allowlist | public |
| PGROONGA_LOCK_TIMEOUT_MS | No | PostgreSQL lock timeout | 1000 |
| PGROONGA_MAX_RESPONSE_BYTES | No | Serialized response limit | 1048576 |
| PGROONGA_STATEMENT_TIMEOUT_MS | No | PostgreSQL statement timeout | 5000 |
| PGROONGA_MAX_NORMALIZATION_INPUT_BYTES | No | Normalization input limit | 16384 |
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 |
|---|---|
| pgroonga_server_infoB | Discover PostgreSQL, PGroonga, Groonga, and feature capabilities. |
| pgroonga_list_indexesB | List catalog-resolved PGroonga indexes and supported search modes. |
| pgroonga_searchC | Execute a bounded, catalog-validated PGroonga search with structured filters. |
| pgroonga_explain_searchB | Return a non-executing EXPLAIN (FORMAT JSON) for a validated search. |
| pgroonga_list_normalization_profilesA | Discover trusted index-level normalizer chains and NormalizerTable dependencies. |
| pgroonga_normalize_textC | Normalize text with a discovered PGroonga index profile. |
| pgroonga_lookup_variantsC | Normalize text and return bounded dictionary variants for the discovered profile. |
| pgroonga_validate_normalization_profileA | Validate dictionary mappings and report normalization hazards without modifying data. |
| pgroonga_healthA | Report limited PGroonga health checks and explicitly unavailable diagnostics. |
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 9 tools
Each tool targets a distinct operation: server info, index listing, search, explain, normalization profiles, text normalization, variant lookup, normalization validation, and health. No two tools appear to do the same thing, and the descriptions make boundaries clear.
All tools share the pgroonga_ prefix and mostly follow a verb_noun pattern (list_indexes, normalize_text, validate_normalization_profile). A few like 'search' and 'health' are simple nouns/verbs, but the overall convention is consistent and predictable.
Nine tools is well-scoped for a domain-specific MCP focused on PGroonga search and normalization. Each tool serves a clear purpose without redundancy or bloat.
The tool surface covers the full workflow: discovering capabilities and indexes, executing and explaining searches, examining normalization, normalizing text, and validating profiles. It lacks explicit search-history or index-creation tools, but for a read-oriented MCP this is complete.