The identity graph as an MCP server. Your AI agents query it natively.
Connect any MCP-compatible AI tool to 287 million organizations, 393 million people and more than 2 billion news articles. MCP 2.0 gives your agent 17 read-only tools and 6 built-in playbooks, so it can research accounts, map markets, build prospect lists and monitor news from a plain-English prompt. No wrapper code, no exports, no copy-paste.
Use the API when your code decides. Use MCP when your agent decides.
The REST API is the right fit when your code decides what to fetch and when: CRM enrichment jobs, data pipelines and services that run the same query on a schedule. MCP fits when an AI agent does the deciding. With the identity graph inside its reasoning loop, the model chooses when to call a tool, traverses corporate family trees to verify subsidiary boundaries and factors in continuously updated market-entry signals, grounded in sourced data drawn from public sources, with a confidence score. Many teams use both: the API for systematic access and MCP for chat-based research.
Four capabilities. One native MCP protocol layer.
Automatic tool discovery
On connection, your agent discovers all 17 tools across organizations, people, news, ontologies, web and guides. You don’t need to know the tool names. The agent picks the right tools for your prompt.
OAuth sign-in
MCP connects through OAuth 2.0: your agent signs in with your GraphIQ.ai account in the browser. For coding tools and systematic access, use the REST API with Bearer authentication.
Token-optimized payloads
Responses carry semantic, pre-resolved entity context shaped to fit model context windows, with structural noise stripped out. The built-in web crawl returns pages clean and compact, using far fewer tokens than general-purpose browsing. Customers report 3x to 11x lower token use with Claude or ChatGPT.
Read-only by design
All 17 tools are read-only, so an agent can explore the graph freely without changing your data. Every place resolves through the Locations Ontology to one canonical name, and regions like EMEA and APAC work as filters.
Playbooks that make agents get it right.
Even strong models make predictable mistakes with B2B data. They guess at industry names, filter out real companies because headcounts are stored as size bands, or count the same company five times because it has five branch offices. Our guides are playbooks the agent reads before it starts. Each one gives the tool sequence, a worked example and the known traps.
- 01
Company research
A grounded pre-call brief covering firmographics, organization relationships, the last 90 days of material news, key executives and a website cross-check.
- 02
Market mapping
The size and shape of a segment (how many companies, where they are, what sizes) before you drill in.
- 03
Prospect lists
A clean territory or account list ranked by size, with branch offices merged into one company, fragments dropped, and every surviving company checked against its own website.
- 04
Find contacts
Named people with work emails at target companies, filtered by seniority and function.
- 05
News monitoring
Funding, M&A, launches and leadership changes for a set of companies, without duplicates.
- 06
Query syntax
A reference for AND/OR/NOT logic, controlled vocabularies, ranges, dates and data caveats.
For multi-step work, name the playbook in your prompt, for example: “Use the prospect lists guide to build me a territory list of…”
We would love to hear what you want to see next. Drop us a line via our website agent. While we don’t respond to every comment, we read them all.
Connect in three steps.
GraphIQ.ai works with Claude, ChatGPT and other AI tools that support remote MCP servers. If you have a paid MCP account, connect to our MCP at https://app.graphiq.ai/mcp.
- Add GraphIQ.ai to your AI tool. In your tool’s connector or MCP settings, add GraphIQ.ai as a remote MCP server using https://app.graphiq.ai/mcp.
- Sign in with your GraphIQ.ai account.
- Ask a question. Your agent picks the tools and, for multi-step work, the playbook.
Three ways to connect to GraphIQ.ai
How does MCP compare to other approaches?
| Approach | What it is | Where it breaks |
|---|---|---|
| CSV Export + RAG | Data export from ZoomInfo/Apollo into a vector store; agent queries embeddings | Data goes stale immediately. No graph hierarchy. Agent retrieves flat text passages, not resolved entities. |
| CRM-as-Context | Agent queries Salesforce or HubSpot directly via native CRM APIs | CRM contains only data your team manually maintains. Fragmented records, no external signal tracking. |
| GraphIQ.ai MCP | Native Model Context Protocol integration into the full identity graph | Continuously updated. Graph-structured. Relationship-native. 17 read-only tools and 6 playbooks. |
Where MCP agent access connects your GTM.
Developers Persona
Building a dedicated engineering toolchain or local agent app? Review our complete SDK configuration guides.
/solutions/developers →AI Agent Data Layer
Looking to eliminate model hallucination loops across your pipeline? See how grounding data layers protect enterprise credibility.
/use-cases/ai-agent-data-layer →Developer Documentation Reference Index
Need complete tool definitions, script samples, and endpoint path parameters?
docs.graphiq.ai →MCP Server
Connection details and client setup for the GraphIQ.ai MCP server.
/resources/mcp-server →Release notes
See what shipped in MCP 2.0, what’s coming next and every release before it.
/resources/changelog →Frequently asked questions
Is our data connection restricted to specific LLM model providers or clients?
No. MCP is a provider-agnostic standard, so the server works with any AI tool that supports remote MCP servers. That includes Claude, ChatGPT, Microsoft Copilot Studio and Cursor. For coding tools and systematic access, the REST API uses Bearer authentication.
Do I need to know the tool names?
No. Your agent discovers all 17 tools when it connects and is good at choosing the right ones for your prompt. For multi-step work, it helps to name the playbook, for example: “Use the prospect lists guide to build me a territory list of…”
Do I need a paid account to use the MCP server?
Yes. If you have a paid MCP account, connect at https://app.graphiq.ai/mcp and sign in with your GraphIQ.ai account.