CitePatch

AI visibility for marketing teams, exposed to your agent.

От сообществаРаботаетБез входаГлобальныйБесплатноМожет изменять данные

Что умеет

Citepatch Apply Patch: Apply an approved patch via connector (opens a reviewable PR/draft). Org mcp_apply_enabled opt-in required. First call without confirmed returns confirmation_required + one-use
Citepatch Get Brand Truth: Returns approved Brand Truth facts for a project. Requires project_id. Facts are verified only when approved in CitePatch.
Citepatch Get Evidence For Gap: Returns the real evidence chain for a gap. Requires project_id and playbook_id, where playbook_id is the stable ID from actionable_gaps (internally the opportunity ID).

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

AI visibility for marketing teams, exposed to your agent. Read the evidence behind how AI assistants answer your buyers' questions (visibility summary, prompt answers, cited pages, competitors), the opportunities and playbooks CitePatch found, Brand Truth, and the reviewable patches — then submit or apply a patch with human approval. OAuth 2.1 with per-scope consent; nothing is published without a person saying yes. A read-only endpoint is available at https://mcp.citepatch.com/mcp/readonly. Requires a paid CitePatch plan. Docs: https://citepatch.com/mcp/

Список инструментов сервера (14)

Технические названия из tools/list. Нужны только разработчикам.

citepatch_apply_patch	Apply an approved patch via connector (opens a reviewable PR/draft). Org mcp_apply_enabled opt-in required. First call without confirmed returns confirmation_required + one-use handle; second call with confirmed=true executes. Audit is fail-closed before the connector write.
citepatch_get_brand_truth	Returns approved Brand Truth facts for a project. Requires project_id. Facts are verified only when approved in CitePatch.
citepatch_get_evidence_for_gap	Returns the real evidence chain for a gap. Requires project_id and playbook_id, where playbook_id is the stable ID from actionable_gaps (internally the opportunity ID). The chain links prompt_id -> gap_identity -> evidence snapshots; playbook_state=missing means no playbook exists. Prefer after citepatch_list_prompts or citepatch_list_opportunities.
citepatch_get_experiment	Returns experiment ledger entries for a project. Requires project_id; optional experiment_id filters to one experiment.
citepatch_get_opportunity	Returns one opportunity by id for a project. Requires project_id and opportunity_id.
citepatch_get_patch	Returns patch details for a project. Requires project_id; optional patch_id filters to one patch.
citepatch_get_patch_brief	Returns the versioned authorship brief (brief_version) for an owned approved opportunity: allowed paths, citable brand_fact_ids, prohibitions, validation battery, and submit schema. Requires project_id and opportunity_id.
citepatch_get_project_briefing	Returns project status briefing (name, domain, onboarding, panel, last measurement). Requires project_id. Do not use for metrics time series — use citepatch_get_visibility_summary.
citepatch_get_prompt_answers	Returns observed AI answers for a prompt_id. External model text is fenced as untrusted data. Requires project_id and prompt_id. Prefer citepatch_list_prompts first to discover prompt_id.
citepatch_get_visibility_summary	Returns AI visibility metrics for a project window. Requires project_id. Metrics include numerator/denominator style cells from CitePatch Monitor — never treat as causal proof.
citepatch_get_workspace	Returns the organization, accessible projects, granted scopes, and connection identity for this token. Input must be empty — never pass organization_id. Use before other tools to discover project_id values.
citepatch_list_opportunities	Lists playbook cards for a project. Requires project_id. When actionable coverage is present, it links prompt_id -> gap_identity -> playbook_state; missing means no playbook exists. Judgements (impact/confidence/effort) are proposed, not measured.
citepatch_list_prompts	Lists tracked prompts (and clusters) for a project so you can discover prompt_id values. actionable_gaps links prompt_id -> gap_identity -> playbook_state; playbook_state=missing means no playbook exists for that gap. Requires project_id. Optional cluster_id and status filters. Prefer before citepatch_get_prompt_answers.
citepatch_submit_patch	Submit an externally authored patch for an owned opportunity. First call without confirmed returns confirmation_required + one-use handle; second call with confirmed=true executes. BeforeSHA is verified against the live connector. Consumes MeterPatches; does not debit generation credits.