Orbilyn MCP server

• Registry namecom.orbilyn/mcpverified in the MCP registry

The registry name sits under orbilyn.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-28
• Tools21
• Server calls itselforbilyn
• Server version1.4.0
• Protocol version2025-03-26

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 327 ms.

• Whether its tools do the product's job has not been judged yet.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score72 of 100answers 94 · definitions 77 · context 100 · connects 100 · lowered by the warning signs below
• Answered100% of days8 of 8 daily checks
• Median first answer1602 ms
• Space in an agent's context≈ 2,077 tokensthe definitions of all its tools (21), which an agent carries on every turn
• Tool definitionsB · 77 of 100
• Typed results0 of 21 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 8 of 21
• Not saying whether it only reads or can destroy: 21 of 21

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• list_integrations

  List Orbilyn channel integrations (metadata only, no secrets).

• list_mismatches

  List mismatches from a comparison run (latest if runId omitted).

• get_monitoring_alerts

  Get unread Monitoring alerts (new mismatches from scheduled runs).

• find_product

  Find a product by SKU and/or EAN with stock and price per channel.

• get_comparison_summary

  Summaries of recent comparison / history runs (counts, labels).

• catalog_health_score

  Catalog health score 0–100 with breakdown: photos, descriptions, prices, stock, duplicates, channel_consistency. Uses the latest comparison run (or setId) plus Overview media signals. Example: {"setId":"<uuid>"}.

• list_critical_issues

  List CatalogIssue rows sorted by impact (severity then type). Default severity=critical. Supports limit + offset pagination. Example: {"limit":20,"offset":0,"severity":"critical"}. Issue shape: sku, channel, type, severity, current…

• prepare_fix_list

  Prepare a CatalogIssue fix list as JSON (default) or CSV. Same schema as list_critical_issues. Example JSON: {"format":"json","limit":50}. Example CSV: {"format":"csv","severity":"all"}.

• ai_readiness_report

  Shopping-agent readiness: catalog products agents would reject (missing GTIN/EAN, photos, description, attributes, price/stock) plus what to fill in. Shared CatalogIssue format. Every result includes rules_version, audit_date…

• explain_issue

  Per SKU: what shopping-agent readiness checks failed and why. Same meta envelope (rules_version, audit_date, checked_fields, profile) + CatalogIssue list + explanations. Example: {"sku":"SKU-100"}.

• get_webhook_config

  Read Scale webhook subscription (URL, enabled, event catalog). Signing: X-Orbilyn-Signature HMAC-SHA256. Webhook sample items use the CatalogIssue schema (sku + type preserved; additive fields).

• configure_webhook

  Configure outbound webhook URL/secret (requires write scope). Events: catalog.duplicate.new, catalog.drift.status, sync.failure, monitoring.*.

• run_monitoring

  Trigger a Monitoring compare run now (requires action scope).

• start_catalog_audit

  Start a catalog audit over persisted comparison/Overview data (no live re-import; safe for large catalogs). Returns auditId + status. Result uses shared CatalogIssue format. Webhook: audit.completed. Requires action scope.

• get_audit_status

  Poll async catalog audit status by auditId (pending|running|succeeded|failed).

• get_audit_result

  Fetch catalog audit result (CatalogIssue list + health). Paginate with limit/offset. Fails if audit is still pending/running.

• create_monitor

  Create a Scale Monitoring pair (Alerty/Automatyzacja). Params: sources, thresholds, issueTypes, actions (webhook|email|fix_list). Write scope.

• update_monitor

  Update an existing Monitoring pair (thresholds, sources, actions, enabled). Write scope.

• pause_monitor

  Pause (disable) a Monitoring pair. Write scope.

• list_monitors

  List Scale Monitoring pairs configured for this account.

• get_monitor_history

  Monitoring run history with deltas vs previous run (new / fixed / open) and CatalogIssue samples.