mcpserve-py
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCPSERVE_DB_PATH | No | Path to SQLite database | data/mcpserve.db |
| MCPSERVE_DATA_DIR | No | Directory for documents and data | data |
| MCPSERVE_LOG_LEVEL | No | Log level (DEBUG, INFO, WARNING, ERROR) | INFO |
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
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| query_databaseA | Execute a read-only SQL query against the SQLite database. Only SELECT statements are allowed. |
| list_tablesB | List all tables in the SQLite database. |
| describe_tableB | Get the schema of a specific table including column names, types, and constraints. |
| create_documentB | Create a new markdown document with optional tags. |
| read_documentC | Read a document by its title. |
| list_documentsB | List all documents, optionally filtered by tag. |
| search_documentsC | Search documents by content and title. |
| get_datetimeA | Get the current date and time, optionally in a specific timezone. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Database Schema | Full database schema (all CREATE TABLE statements) |
TDQS
Scored across 8 tools
Most tools target clearly distinct resources and actions, so an agent can pick correctly with little hesitation. The only mild overlap is between list_documents (tag filter) and search_documents (content/title query), which descriptions do disentangle.
Every tool follows a clean verb_noun snake_case pattern: query_database, list_tables, describe_table, create_document, read_document, list_documents, search_documents, get_datetime. No deviations or mixed conventions.
Eight tools is well-scoped for a lightweight multi-purpose server covering database introspection, document management, and a datetime utility. Each tool earns its place with no redundancy.
Document handling lacks update and delete operations, and the database surface is read-only with no insert/update/delete, so lifecycle coverage is partial. The lone get_datetime tool also sits outside either domain, leaving a somewhat heterogeneous surface.