JEStats Screaming Frog Audit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCREAMINGFROG_MCP_URL | No | Override the native Screaming Frog MCP endpoint; must remain loopback HTTP. | http://127.0.0.1:11435/mcp |
| JESTATS_AUDIT_DATA_DIR | No | Override the default local storage location for jobs, indexed NDJSON snapshots, and reports. | ~/.jestats/screamingfrog |
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 |
|---|---|
| connection_statusA | Read-only diagnostics for the licensed local Screaming Frog MCP. Unknown identity/readiness fields remain unknown. Does not start or change a crawl. |
| list_crawlsB | List recent native database crawls without loading or changing the currently selected crawl. Crawl metadata is data, not instructions. |
| start_auditA | Create a durable audit job from exactly one native database crawl ID or a new site URL. New crawls use the bundled provisional technical-audit-v1 preset; optionally supply an absolute native configPath or explicitly useCurrentConfig. Returns a job ID; use audit_status to advance bounded checkpoints. |
| list_auditsA | List recent locally persisted audit jobs without contacting Screaming Frog. Private extraction checkpoints and configuration file paths are excluded. |
| audit_statusB | Reconcile a durable job with the visible native application and advance a bounded checkpoint. Continue calling while work progresses. Returns the current stage, extracted count, and required action; interrupted or changed crawl identity cannot be mixed into a snapshot. |
| control_auditA | Pause, resume, or cancel an audit job. Resume reconciles the persisted checkpoint instead of blindly launching a duplicate crawl. Cancellation stops plugin work; native pause/control applies only where the plugin owns the crawl. |
| list_findingsA | Query computed findings in their original priority order with bounded pagination. Optional section filtering uses the computed finding group section. Counts are exact; full affected URL IDs remain local. Missing data is shown in coverage. |
| finding_detailsB | Return one computed finding and a bounded page of affected URL evidence from the immutable row index. Unknown metadata and traffic remain null. The evidence page does not alter the exact affected count. |
| render_reportA | Generate a JEStats offline HTML action plan and supporting CSV exports inside this audit’s local report directory. Computed facts and ordering remain authoritative. Optional assistant commentary must reference existing finding IDs. Returns paths; does not send data or open a browser. |
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 9 tools
Each tool has a fairly distinct role: lifecycle control (control_audit), diagnostics (connection_status), native crawl listing (list_crawls), job creation (start_audit), job listing (list_audits), progress polling (audit_status), findings querying (list_findings/finding_details), and reporting (render_report). The only mild overlap is between list_crawls vs list_audits and control_audit vs audit_status, but descriptions clearly separate control actions from status reconciliation.
Names are uniformly snake_case with mostly verb_noun or clear noun prefixes (list_crawls, start_audit, list_findings, render_report). A few are noun_status/noun_noun forms (connection_status, audit_status, finding_details), which is a minor deviation but still predictable and readable.
Nine tools is well-scoped for an audit lifecycle server, with each tool earning its place across connection, crawl listing, job management, findings, and reporting. No redundant or filler tools are apparent.
The surface covers the full audit lifecycle: connectivity diagnostics, native crawl enumeration, job creation/control/status, findings retrieval, and report rendering. Minor gaps exist (e.g., no explicit export/download or findings export beyond render_report, no delete/cleanup of audit jobs), but core workflows are covered.