Skip to main content
Your client lists every available tool automatically (tools/list) with full input schemas, you rarely need to call one by name. This page is the map of what’s available, the scope each requires, and how calls are metered.
Every tool is org-scoped to your authenticated session. Org context comes from your token or API key, never from a tool argument, so an agent can’t read or change another organization’s data. Reference-data tools (offices, jurisdictions, classifications, rules) are global public data, not org-scoped, but still require a scope like other reads.
ToolWhat it doesRead/Write
search_trademarksSearch global registrations by name, owner, Nice class, jurisdiction, or status. Exact, phonetic, fuzzy, and prefix matching across production offices.Read
suggestQuick typeahead across trademarks, owners, attorneys, and firms, compact results for disambiguation.Read

Trademarks

ToolWhat it doesRead/Write
get_trademarkFull detail for one mark by ID, owners, attorneys, classifications, events, media.Read
list_trademarksList marks with filtering and sorting (use search_trademarks for text search).Read
get_trademark_historyProsecution event timeline for a mark (filings, publications, registrations, status changes).Read
get_trademark_changesField-level diffs between record updates, and when each happened.Read
get_trademark_relatedMark-to-mark relationships: Madrid designations, divisionals, seniority claims, transformations.Read
get_trademark_proceedingsProceedings involving a mark (oppositions, cancellations), each with its parties.Read
get_trademark_coverageJurisdictional coverage, Madrid designation territories and protection status.Read
get_trademark_sourceProvenance: source office, observation date, and source format.Read
batch_get_trademarksFetch full detail for up to 100 marks by ID in one call, with a not_found list for anything that didn’t match.Read

Owners & entities

ToolWhat it doesRead/Write
get_ownerOwner (applicant/registrant) detail with portfolio statistics.Read
list_ownersSearch and list owners, find companies or individuals who hold marks.Read
get_owner_trademarksAn owner’s trademarks (summary tier) with filtering and sorting.Read
get_owner_relatedOwners related via the GLEIF corporate hierarchy (parent/child).Read
get_entityA resolved entity: the cross-office identity over per-office owner clusters, with link evidence and public-company facts.Read
list_entitiesSearch resolved entities (one company across all offices), filterable by public-company facts.Read
get_entity_trademarksA resolved entity’s trademarks fanned across all member owners.Read
get_entity_familyA resolved entity’s direct GLEIF corporate family (parent and direct subsidiaries).Read

Attorneys & firms

ToolWhat it doesRead/Write
get_attorneyDetail for an attorney or representative of record.Read
list_attorneysSearch and list attorneys and representatives.Read
get_attorney_trademarksAn attorney’s trademarks (summary tier) with filtering and sorting.Read
get_attorney_clientsOwners an attorney represents, each with a shared-mark count.Read
get_firmLaw-firm detail, including portfolio and attorneys.Read
list_firmsSearch and list law firms, ranked by portfolio size or attorney count.Read
get_firm_attorneysA firm’s attorneys, each with portfolio stats.Read
get_firm_trademarksTrademarks handled by a firm’s attorneys (summary tier).Read

Proceedings

ToolWhat it doesRead/Write
get_proceedingDetail for one proceeding (opposition, cancellation, etc.) by ID (e.g. prc_8kLm2nPq).Read
list_proceedingsList TTAB oppositions, cancellations, and other proceedings with filtering.Read

Reference data

Global, public reference data. Not org-scoped, but still requires a read scope, and is logged but not billed.
ToolWhat it doesRead/Write
list_officesSupported trademark offices, with jurisdiction coverage.Read
get_officeA single office by its lowercase office code (e.g. uspto, euipo, wipo).Read
list_jurisdictionsSupported jurisdictions (ISO-2 plus regional/WIPO codes), with Madrid membership and live-office coverage.Read
get_jurisdictionA single jurisdiction by code, including Madrid membership and member jurisdictions.Read
get_deadline_rulesMaintenance/renewal deadline rules with statutory citations; optionally per jurisdiction.Read
get_opposition_rulesOpposition window rules with citations, duration, and time zone; optionally per jurisdiction.Read
list_classificationsNice classification classes (the 45-class WIPO standard), filterable by category or keyword.Read
suggest_classificationsSuggest Nice classes for a natural-language description, ranked with confidence and rationale.Read
list_goods_servicesBrowse/search the curated goods & services term catalog.Read
suggest_goods_servicesDraft filing-ready goods/services wording per Nice class from a description.Read
list_design_codesVienna classification design codes (figurative-element taxonomy for logos/devices).Read
get_design_codeA single Vienna design code with notes and its child codes.Read

Account & usage

Utility tools for your own org’s account and consumption. Neither billed nor counted against quota.
ToolWhat it doesRead/Write
get_usageCurrent billing-period usage plus the per-endpoint-type quota and rate-limit matrix.Read
get_usage_summaryDaily usage breakdown (requests, billed units, errors, average latency).Read
get_accountOrg identity (ID, name, plan, key scopes and rate-limit tier) with the plan quota breakdown.Read

Monitoring

Watches, alerts, and webhooks. Billed at zero request-level cost; watch capacity itself is capped by your plan.
ToolWhat it doesRead/Write
signa_watches_listList monitoring watches for your org (cursor-paginated).Read
signa_watches_retrieveRetrieve a single watch by ID.Read
signa_watches_createCreate a watch (same validation as POST /v1/watches).Write
signa_watches_updateUpdate a watch (PATCH semantics, omitted fields unchanged).Write
signa_watches_deleteDeactivate a watch (soft-delete).Write
pause_watchPause a watch (stops new alerts).Write
resume_watchResume a paused watch.Write
preview_watchDry-run a watch query: estimate matches and preview marks. No watch is created.Read
get_watch_diagnosticsAudit-mode provenance trace for one (watch, trademark) pair.Read
signa_alerts_listList monitoring alerts for your org.Read
signa_alerts_retrieveRetrieve a single alert by ID.Read
list_alerts_for_watchList alerts emitted by a single watch (cursor-paginated).Read
lookup_alertBulk-fetch up to 100 alerts by ID (polling pattern).Read
signa_webhooks_listList webhook endpoints (secrets are never returned).Read
signa_webhooks_retrieveRetrieve one webhook endpoint (secret redacted).Read
Webhook secrets are never exposed through MCP, signa_webhooks_list and signa_webhooks_retrieve always redact them. Manage secrets via the REST API instead.

Scopes

ScopeGrants access to
trademarks:readEvery search, trademark, owner, entity, attorney, firm, proceeding, and reference-data tool above.
billing:readAccount & usage tools: get_usage, get_usage_summary, get_account.
portfolios:manageEvery monitoring tool, reads and writes alike: watches, alerts, and webhooks.
offline_accessKeeps an OAuth session’s token refreshing silently. Doesn’t grant tool access on its own.
Most clients request trademarks:read by default, which covers every data and reference tool. Add billing:read if you want your agent to inspect usage and account details, and portfolios:manage only if you want it to read or change watches, alerts, and webhooks. If a tool needs a scope your session lacks, the call returns a clear error naming the required scope, and the rest of the session keeps working.

Metering

MCP tool calls are metered like REST requests: each call counts against your plan’s quota and appears in your usage and request logs, classified the same way its REST counterpart is (search, read, monitoring, and so on). Search and read tools cost 1 unit; suggest_goods_services costs 2; batch_get_trademarks costs 1 unit per ID (up to 100). Reference-data tools are logged but not billed. Account and usage tools are neither billed nor counted. Over-quota calls return a clear error naming the limit that was hit and when it resets, instead of running the tool. The initialize and tools/list handshake calls are never metered.

Rate limits

MCP requests share a dedicated rate-limit tier of 1,000 requests per minute, separate from your plan’s per-endpoint-type limits. See Rate limits for the full header semantics. If you hit the limit, the response includes a Retry-After header.

Security

  • Org isolation. Org context is resolved from your token or API key on every request, never from a tool argument. An agent cannot read or modify another organization’s data, even if prompted to.
  • Least privilege. Scopes are enforced per tool. For read-only use, issue an API key without portfolios:manage so the watch, alert, and webhook write tools are unavailable.
  • Review tool calls. Most MCP clients let you approve tool calls before they run. Keep approval on for any agent with portfolios:manage, and treat tool results as data an untrusted prompt could try to act on.

Troubleshooting

Your MCP client is not sending the access token. Re-authenticate by removing and re-adding the MCP connection.
Your Signa account has not completed onboarding. Log in at app.signa.so and create an organization first.
Your token has expired. Most MCP clients handle refresh automatically. If the error persists, remove and re-add the connection to re-authenticate.
You are sending more than 1,000 MCP requests per minute. Wait for the Retry-After period or reduce request frequency.