dblink
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DBLINK_BIND | No | Bind address; 0.0.0.0 must be explicit. | 127.0.0.1 |
| DBLINK_PORT | No | HTTP port (or pass --http <port>). | 7331 |
| DBLINK_IDLE_MS | No | Idle pool eviction in milliseconds (15 min). | 900000 |
| DBLINK_MAX_POOLS | No | Max distinct connection pools per process. | 20 |
| DBLINK_POOL_SIZE | No | Max clients per pool. | 5 |
| DBLINK_HTTP_TOKEN | No | Bearer token required when --http is used; the server refuses to start without it. |
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 |
|---|---|
| open_connectionA | Open (or reuse) a database connection. Returns a connection_id used by the other tools. DSN schemes: postgres://, mysql://, redis://, mongodb://, mongodb+srv://, sqlite: |
| close_connectionC | Close a connection and release its pool. |
| list_connectionsA | List active connections with alive/dead status. |
| db_queryB | Run a read-only SQL statement (SELECT/SHOW/EXPLAIN/read-only WITH) and return rows. |
| db_executeB | Run a write statement on a writable connection (read_only=false). Returns affected_rows. |
| db_list_tablesC | List tables/views in the connected database. |
| db_describe_tableB | Describe a table: columns (name/type/nullable/default) and indexes. |
| redis_commandB | Run a read-only Redis command (allow-list). Writes return UNSUPPORTED. |
| mongo_findC | Query documents from a MongoDB collection. filter/projection/sort accept relaxed EJSON. Returns relaxed EJSON documents. |
| mongo_aggregateC | Run a MongoDB aggregation pipeline. Read-only connections reject $out/$merge. |
| mongo_writeB | Write to MongoDB (action: insert|update|delete). Only allowed on writable connections (read_only=false). |
| mongo_list_collectionsC | List collections in a MongoDB database. |
| mongo_describe_collectionB | Describe a MongoDB collection: sample document (EJSON), indexes and inferred fields. |
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 13 tools
MongoDB, SQL, and Redis operations are clearly separated by tool prefixes and descriptions, so an agent can usually select the right backend. Minor overlap remains between read/query tools like mongo_find, db_query, and redis_command, and between the Mongo/SQL list/describe pairs, but the database family disambiguates them.
Most tools follow a predictable family-prefix plus action pattern: mongo_*, db_*, and connection lifecycle verbs like open_connection/close_connection/list_connections. There are small deviations such as mongo_find vs db_query vs redis_command, but the overall scheme is readable and consistent.
The 13 tools are well-scoped for a multi-database connector, with connection management plus a focused set of read, write, list, and describe operations per backend. No tool appears redundant enough to remove, and the count stays within a manageable range.
The surface covers connection lifecycle, SQL read/write and introspection, MongoDB query/aggregate/write/introspection, and Redis read-only commands. Gaps remain around Redis writes, SQL DDL/transaction operations, and broader MongoDB administration, but core database workflows are covered.