Qingflow MCP (CRUD)
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QINGFLOW_BASE_URL | Yes | Base URL of the Qingflow API | |
| QINGFLOW_EXPORT_DIR | No | Directory for exports | /tmp/qingflow-mcp-exports |
| QINGFLOW_ACCESS_TOKEN | Yes | Access token for authentication | |
| QINGFLOW_ADAPTIVE_PAGING | No | Enable adaptive paging (1 or 0) | 1 |
| QINGFLOW_EXPORT_MAX_ROWS | No | Maximum rows for export | 10000 |
| QINGFLOW_FORM_CACHE_TTL_MS | No | Form cache TTL in milliseconds | 300000 |
| QINGFLOW_REQUEST_TIMEOUT_MS | No | Request timeout in milliseconds | 18000 |
| QINGFLOW_EXECUTION_BUDGET_MS | No | Execution budget in milliseconds | 20000 |
| QINGFLOW_ADAPTIVE_MIN_PAGE_SIZE | No | Minimum page size for adaptive paging | 20 |
| QINGFLOW_ADAPTIVE_TARGET_PAGE_MS | No | Target page time in milliseconds for adaptive paging | 1200 |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| qf_tool_spec_getA | Return MCP tool parameter requirements, limits, aliases and minimal examples for agent prompt grounding. |
| qf_form_getC | Get form metadata and compact field summaries for one app. |
| qf_field_resolveB | Resolve natural language field names/aliases into stable que_id mappings for one app. |
| qf_value_probeA | Probe likely field values for one app field, with explicit match mode and matched value evidence. |
| qf.query.planB | Preflight canonical query DSL, normalize loose inputs, translate into internal tools and estimate whether the query is ready for a final conclusion. |
| qf.query.rowsC | Query rows through the canonical DSL and return query handles plus resource links. |
| qf.query.recordC | Fetch one record through the canonical DSL and return a query handle. |
| qf.query.aggregateB | Aggregate records through the canonical DSL and return metrics_by_column plus query handle resources. |
| qf.records.mutateC | Canonical write entry for create/update operations. |
| qf.query.exportA | Export canonical row queries and return resource links instead of large inline payloads. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze-period-comparison | Build a structured comparison workflow for two time ranges using qf.query.plan and qf.query.aggregate. |
| build-query-from-question | Turn a natural language request into canonical Qingflow query DSL, then verify it with qf.query.plan. |
| prepare-record-write | Prepare a canonical qf.records.mutate payload from human field descriptions, then write only after validation. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/853046310/qingflow-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server