Connect your AI agent

Tools reference

Every tool the Prominara MCP server exposes, with its permission and what it can spend.

Last updated

The server exposes 14 tools in the prominara_ namespace. Read tools need the read permission, act tools need write. This table is generated from the server’s own catalog, so it cannot drift from what your agent sees.

Read tools

List sites

prominara_list_sites

Lists the sites (brands) in the connected Prominara organization with domain, brand name, latest audit score, last scan date and active prompt count. Call this first to learn which site identifiers to use with the other tools; sites can be addressed by domain or id.

read permissionNo quota

Visibility overview

prominara_visibility_overview

Returns AI-search visibility for one site over a window (default 30 days): citation and mention rates with confidence intervals, per-platform breakdown, trend versus the previous window, and the competitor ranking. Rates use earned prompts and successful checks only. Use concise for headline numbers, detailed for per-prompt rows.

read permissionNo quota

List tracked prompts

prominara_list_prompts

Lists the prompts tracked for a site with category, panel (organic, branded, competitive), active state and the latest result per platform. Filter by status or search text. Use it to find prompt ids before calling get_answers, run_check or set_prompt_active.

read permissionNo quota

Get latest AI answers

prominara_get_answers

Returns the latest recorded AI answers for one prompt: per platform whether the brand was mentioned or cited, the sources the answer used, position and sentiment, plus check history. Detailed mode includes the answer text, returned as untrusted third-party content.

read permissionNo quota

List missions

prominara_list_missions

Lists the prioritized missions for a site: for each tracked prompt, the current visibility, the page that should own the answer (or the gap), the source gap and the next best action, ranked by priority. Filter by priority, status or intent.

read permissionNo quota

Sources intelligence

prominara_sources

Returns the off-site sources behind AI answers for a site. Views: domains (which sites AI answers cite and whether they mention the brand), citations (individual cited pages), opportunities (ranked places to earn a citation) and accuracy (factual issues found in answers about the brand).

read permissionNo quota

Measurement verdicts

prominara_measurement

Returns the impact measurement for content changes logged on a site: per change, the observation window status and the verdict (likely lift, no effect, still collecting) with its probability, plus the program-level before/after comparison when enough data exists. Pass a change id for the detail of one change. Verdict wording is the product's own and does not claim causation beyond what the design supports.

read permissionNo quota

Suggest prompts to track

prominara_suggest_prompts

Returns suggested prompts for a site from the coverage matrix (organic, branded and competitive panels across buyer-journey stages), with a recommended set for the plan's slots. Uses the cached set when one exists; generating a fresh set counts against the AI suggestion allowance.

read permissionAI suggestion allowance

Plan and usage

prominara_usage

Returns the organization's plan, monthly check quota used and remaining with the reset date, tracked prompt slots used, platform slots and trial state. Call it before running checks or creating prompts to know what fits.

read permissionNo quota

Act tools

Create tracked prompts

prominara_create_prompts

Adds up to 20 prompts to track for a site and triggers their first checks. Duplicates of existing prompts are skipped, prompts beyond the plan's slots are skipped and reported, and platforms are clamped to the plan. Returns what was created, what was skipped and why.

write permissionPrompt slots

Run a check now

prominara_run_check

Runs a fresh visibility check for up to 10 prompts across the site's enabled AI platforms, exactly like "Run now" in the app. Each check counts against the monthly quota. Prompts with a check already in progress are skipped and reported. Results arrive asynchronously; read them with get_answers after a minute or two.

write permissionCheck quota

Log a shipped content change

prominara_log_content_change

Records that a page on the site was changed (edited, published, structured data added) with the release date and a summary, so Prominara can measure its impact on AI visibility. Creates the before/after experiment and freezes the affected prompts. Logging the same page and date twice returns the existing change.

write permissionOpens a measurement window

Update mission status

prominara_update_mission

Sets the status of one mission (per prompt) on a site: new, in_progress, shipped, snoozed (with a date) or dismissed. Use shipped after the page work is live, or log_content_change which does it automatically.

write permissionNo quota

Enable or disable prompts

prominara_set_prompt_active

Activates or deactivates up to 50 tracked prompts. Deactivated prompts stop being checked and free a slot; activating re-checks the plan's prompt slots and reports any that do not fit.

write permissionPrompt slots

Addressing sites and prompts

Sites can be named by domain or by id. Call the list-sites tool first if you are not sure which identifier to use. Prompts are addressed by id, which the list-prompts tool returns.

Concise and detailed output

Tools whose output can be large accept a response format. Concise returns headline numbers and top rows, detailed adds per-prompt detail. Recorded answer text is only returned in detailed mode, truncated, and wrapped as untrusted third-party content so the calling agent treats it as evidence rather than instructions.

Limits per call

  • Create prompts: up to 20 per call
  • Run a check: up to 10 prompts per call
  • Enable or disable prompts: up to 50 ids per call
  • List tools: a limit of at most 100 rows

Errors say what to do next

A refusal is never a bare failure. Each one carries a code, a plain sentence your agent can relay, and the numbers behind it, so you learn which limit was reached and when it resets rather than watching a call fail silently. Partial success is reported too: if three of five prompts fit your plan, the tool creates three and says why the other two were skipped.

Was this page useful?