All documentation
- All documentation
- Features
- Integrations
- API and MCPGetting startedInterfaces
- Account and settings
Give your AI client your visibility data
CiteAgentic runs a Model Context Protocol server, so Claude, Cursor and any other MCP client can read your scans, prompts, competitors and recommendations — and run new scans — without you copying anything across.
What is the CiteAgentic MCP endpoint?
It is POST https://citeagentic.com/mcp. The server speaks JSON-RPC over Streamable HTTP at that single endpoint:
POST https://citeagentic.com/mcp
Authorization: Bearer <your CiteAgentic API key>
GET /mcp answers 405 on purpose — this is a POST-only transport.
One key works for both the MCP server and the REST API — there is one credential, not two. See Authentication for how to get one and how scopes work.
What tools does the MCP server expose?
Twenty-seven tools, grouped by what they touch.
| Area | Tools |
|---|---|
| Sites | cite_list_sites, cite_get_portfolio_summary, cite_get_site_brief |
| Scans | cite_get_latest_scan, cite_get_scan_status, cite_run_visibility_scan, cite_run_audit_scan |
| Audit | cite_get_audit_scores, cite_get_audit_findings |
| Visibility | cite_get_visibility_scores |
| Prompts | cite_list_prompts, cite_get_prompt_detail, cite_generate_prompts, cite_refine_prompt, cite_get_prompt_competitor_results |
| Competitors | cite_list_competitors, cite_add_competitor, cite_get_competitor_gaps, cite_run_competitor_comparison |
| Recommendations | cite_get_recommendations |
| Content | cite_get_content_opportunities, cite_generate_content_draft, cite_get_voice_profile |
| Buyer evidence | cite_get_review_themes, cite_get_buyer_criteria, cite_get_positioning_claims |
| Agent | cite_ask |
What scopes does each tool need?
Each tool declares the scope it needs, and a key only carries the scopes you grant it. Read and write are separated, and so is running work that costs credits.
| Scope | Grants |
|---|---|
read:sites | Site list, portfolio summary, site brief |
read:visibility | Visibility scores and history |
read:audits | Audit scores and findings |
read:prompts | Prompt list and per-prompt detail |
read:competitors | Competitor list and gap analysis |
read:recommendations | The recommendation queue, including fix prompts |
read:content | Content opportunities and drafts |
read:voice | Voice profile, review themes, buyer criteria |
write:prompts | Generate and refine prompts |
write:competitors | Add a competitor |
write:content | Generate a content draft |
run:visibility | Start a visibility scan |
run:audits | Start an audit scan |
Grant the narrowest set that does the job. A key that only needs to report on visibility does not need run: scopes, and a scan started by mistake spends credits.
What should I know before wiring up MCP?
Scans are rate-limited per site. A visibility scan started through MCP respects a one-hour cooldown, the same as one started in the app. A second request inside that window returns the existing run rather than starting a duplicate and billing you twice.
Write tools accept an idempotency key. Pass idempotencyKey on a tool that creates something and a retry returns the original result instead of creating a second copy. Worth using: agent loops retry more than people do.
Every call is recorded against the key that made it, so you can see which client did what.
Quotas are the plan's quotas. Prompts, competitors and drafts count against the same limits as the UI. MCP is another way into the same account, not a way around it.