crawldata-engine
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | LLM model name used for PDF report extraction, e.g. deepseek-v4-flash. | |
| DC_API_KEY | No | API key for Google Data Commons access. | |
| LLM_API_KEY | No | LLM API key. Takes precedence over OPENAI_API_KEY when both are set. | |
| PANEL_TOKEN | No | When set, /panel/* requires this token via header X-Panel-Token, ?token=, or cookie. | |
| SCRAPYD_URL | No | Scrapyd URL used by the scrapyd launcher. | |
| LLM_BASE_URL | No | LLM provider base URL used for PDF report extraction. Current provider is DeepSeek on Ark. | |
| FINDDATA_ROOT | No | Optional path to a local datasource workspace for providers that need it. The in-code seed catalog works without it. | |
| EDGAR_IDENTITY | No | Identity email required before using SEC EDGAR data, e.g. your_email@example.com. | |
| OPENAI_API_KEY | No | Legacy API key accepted for LLM usage. LLM_API_KEY wins when both are set. | |
| SCRAW_PLAN_DIR | No | Plan directory used by the scrapyd launcher. | |
| POLYGON_API_KEY | No | API key for Polygon.io data access. | |
| SCRAW_K8s_IMAGE | No | Container image used by the k8s launcher. Exact casing is as documented: SCRAW_K8s_IMAGE. | |
| FD_PROXY_FORWARDER | No | Proxy forwarder setting. Empty for local dev; cluster crawling uses the standalone fd-proxy-service forwarder. | |
| POLICY_MAX_FETCHES | No | Plan-size guardrail. A due policy whose fetch estimate exceeds this is rejected unless the policy sets force. | 50000 |
| RECONCILER_LAUNCHER | No | Launcher for crawl plans: scrapyd (default) or k8s. | scrapyd |
| SCRAW_K8S_NAMESPACE | No | Kubernetes namespace used by the k8s launcher. | |
| SCRAW_K8S_REDIS_URL | No | Redis URL used by the k8s launcher. | |
| SCRAW_K8S_DATABASE_URL | No | Database URL used by the k8s launcher. | |
| FD_OPEN_DATA_MCP_DATABASE_URL | No | Database URL. Defaults to the SQLite path fd_open_data_mcp/metadata/daas.db; Postgres is recommended for production. |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues