live-mcp-for-1c
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LIVE_MCP_FOR_1C_CACHE_ROOT | No | Absolute directory for XLSX artifacts. Defaults to $HOME/.cache/live-mcp-for-1c. | |
| LIVE_MCP_FOR_1C_VERIFY_TLS | No | Whether to verify TLS. Defaults to true. | true |
| LIVE_MCP_FOR_1C_HTTP_TIMEOUT_SECONDS | No | HTTP timeout in seconds. Defaults to 60; does not cancel server-side execution. | 60 |
| LIVE_MCP_FOR_1C_HTTP_SERVICE_BASE_URL | Yes | Base URL of the 1C HTTP service, including the service root and without a trailing slash. | |
| LIVE_MCP_FOR_1C_HTTP_SERVICE_PASSWORD | Yes | Password for the 1C infobase HTTP service; provide only via environment variables or a secret store. | |
| LIVE_MCP_FOR_1C_HTTP_SERVICE_USERNAME | Yes | Username for the 1C infobase HTTP service. |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| validate_1c_queryC | Parse and admit a read-only 1C query without executing it. |
| execute_1c_queryC | Execute an admitted read-only 1C query through AIDataRead. |
| execute_dcs_schemaC | Execute a supported Data Composition Schema into a value collection. |
| render_dcs_schemaC | Render a supported Data Composition Schema and optionally persist XLSX. |
| ping_serviceB | Check AIDataRead service availability through GET /ping/. |
| get_service_infoA | Read AIDataRead version, endpoints, auth, limits, and capabilities. |
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 6 tools
Each tool pairs a distinct verb with a distinct target: execute vs validate for 1C queries, execute vs render for DCS schemas, and ping vs get_service_info for service introspection. The main risk is confusing execute_dcs_schema with render_dcs_schema and ping_service with get_service_info, but the descriptions clearly separate their outputs (value collection vs XLSX, availability vs metadata).
All six tools follow a consistent verb_noun convention (execute_1c_query, validate_1c_query, execute_dcs_schema, render_dcs_schema, ping_service, get_service_info). The embedded domain tokens (1c, dcs) are used consistently within their families, making the pattern predictable.
Six tools is well-scoped for a read-only 1C data-access service: two query operations, two DCS operations, and two introspection tools. Every tool earns its place with no redundant surface.
Core lifecycle covers validate→execute for queries and execute→render for DCS, plus health and metadata discovery. Minor gaps remain, such as no schema/metadata browsing to discover available tables or fields before writing a query, forcing reliance on get_service_info or trial-and-error validation.