scope

Tool reference

The 14 Scope agent tools.

The public API-of-record for the Scope MCP server. Every tool below is available at the same endpoint over Streamable HTTP.

https://scope.online/mcp

See

whoamirequires readFree

Returns plan, remaining checks, committed burn, auto-upgrade state, and rate-limit status.

list_businessesrequires readFree

Lists businesses on the account with their latest snapshot and scheduled burn.

get_visibility_reportrequires readFree

Returns the overall visibility score, per-engine breakdown, and trend over time.

get_prompt_resultsrequires readFree

Returns paginated, prompt-level measurements and cadence.

get_citationsrequires readFree

Returns cited sources across engines and competitor citation gaps.

get_competitorsrequires readFree

Returns the measured competitor set and share-of-voice signals.

get_recommendationsrequires readFree

Returns prioritized fixes with their expected impact.

get_readiness_scorerequires readFree

Scores a website’s readiness for AI visibility; a limited anonymous check is available with no login.

Do

add_businessrequires business:writeFree

Idempotently adds a business by normalized domain.

run_scanrequires scan:run1 check per tracked prompt

Runs every tracked prompt across all supported engines.

check_promptrequires scan:runExactly 1 check

Tests a single prompt across engines without tracking it.

track_promptrequires scan:runFree now — adds committed burn

Commits a prompt to monthly or weekly monitoring for a business.

untrack_promptrequires scan:runFree

Removes a tracked prompt from a business, reducing committed burn.

Fix

generate_fixrequires readFree

Drafts schema, FAQ, or content from a recommendation; never writes to the site.

complete_recommendationrequires business:writeFree

Marks a recommendation complete with an optional note, for before/after attribution.

The checks contract

A check is one prompt evaluated across all supported engines.

check_prompt spends exactly one check. run_scan spends one check per tracked prompt included.

Adding a prompt with track_prompt is free at that moment — its cadence creates committed burn (monthly cadence commits 1 check/month; weekly commits about 4/month).

Every response that spends checks returns checks_spent and checks_remaining — relay them to the human, and warn at 80% pool use.

There is no publish_fix tool. Scope agents draft fixes; they never publish directly to a website or CMS.

Error shapes

Every error returns a JSON-RPC error with a stable machine-readable code.

codestatusmeaning
invalid_request400Malformed or missing required arguments.
unauthorized401Missing, expired, or invalid API key / OAuth token.
insufficient_scope403The key or token is missing a required permission (e.g. business:write).
tier_locked403The account is not on Growth. Relay the returned upgrade_url and stop.
not_found404The business, prompt, or recommendation ID does not exist on this account.
rate_limited429Too many requests. Respect retry_after (seconds) before retrying.
quota_exceeded402The account's check pool is exhausted. Do not retry or split the action.
over_committed402Existing tracked prompts already exceed the plan pool. Offer to reduce cadence.
internal_error500Unexpected server error. Safe to retry once.

Rate limits

Read tools

60 requests / 60 seconds

per authenticated user

Action tools

10 requests / 60 seconds, 500 / day

per authenticated user

Anonymous readiness check

5 requests / 24 hours

per source IP

A rate_limited response includes retry_after in seconds.

15 tools total. See the full setup flow, example prompts, and trust model.

Back to Scope for agents