> For the complete documentation index, see [llms.txt](https://help.delpha.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.delpha.io/delpha-api-and-mcp/delpha-api-and-mcp.md).

# Delpha API & MCP

Integrate Delpha's data quality and enrichment engines into your custom applications via our REST API, or connect local LLMs and AI agents to your business data using the Delpha MCP server.

## Delpha API & MCP

Welcome to the Delpha Developer Hub. While Delpha offers a native application for Salesforce, our core data quality, deduplication, and enrichment engines are built API-first.

This section provides all the technical documentation, endpoints, and configuration guides you need to extend Delpha's capabilities into your own custom software, proprietary data pipelines, or advanced AI workflows.

> **New to Delpha?** Start with [How Delpha works — resolution, evidence, confidence, credits](/core-concepts/how-delpha-works-resolution-evidence-confidence-credits.md) for the shared concepts, and the [Use Cases](/use-cases/ultimate-parent.md) section for what each verification means — the API and MCP return the same payloads documented there.

Choose your integration method below to get started.

### Start here: MCP or REST API?

| Your goal                                                              | Use                                                                                                                           |
| ---------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
| Let an agent verify one company or contact                             | [**MCP**](/delpha-api-and-mcp/mcp.md) — connect below and discover the tools through your client.                             |
| Run batches, search the company datalake, or send an `Idempotency-Key` | [**REST API**](https://help.delpha.io/delpha-api-and-mcp/api) — these capabilities are not MCP tools.                         |
| Try verification with canned results and no credit spend               | [**REST test mode**](https://help.delpha.io/delpha-api-and-mcp/api/test-mode) — MCP's API-backed tools reject test-mode keys. |
| Teach an agent a repeatable workflow                                   | [**An agent skill**](/delpha-api-and-mcp/mcp.md#use-delpha-in-an-agent-skill) together with an authenticated MCP connection.  |

***

### Delpha REST API

Integrate Delpha’s powerful data processing directly into your custom applications, internal dashboards, or alternative CRMs. Our API allows you to programmatically trigger data quality checks, retrieve structured enrichments (like Company Legal IDs or Contact information), and manage data normalization at scale.

**What you will find here:**

* Authentication & API Key management
* Core endpoints for evaluation and enrichment
* Handling structured JSON payloads and recommendation data
* Rate limits and best practices

👉 **Explore the** [**API Documentation**](/delpha-api-and-mcp/api.md)

***

### Delpha MCP (Model Context Protocol)

The Model Context Protocol (MCP) is an open standard that lets AI models and agents call external tools securely. Delpha runs a **hosted MCP server** at `https://mcp.delpha.ai/mcp`: connect Claude, ChatGPT, Claude Code, Cursor, VS Code, Windsurf or Codex to it, sign in with your Delpha account (or use an API key), and your agent gets the same Find, Validate and Enrich tools as the REST API — no installation, no local server.

**What you will find here:**

* Connecting each client to the hosted server (one URL, sign in with Delpha)
* The 16 tools, grouped by workflow, with the API-key scope each one needs
* Team access, connected clients and API keys in the console (Developer → MCP)
* Release notes for the MCP server

👉 **Explore the** [**MCP Documentation**](/delpha-api-and-mcp/mcp.md)

***

> 💡 **Want to know more?** Platform, pricing, and credits: [delpha.ai](https://delpha.ai)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.delpha.io/delpha-api-and-mcp/delpha-api-and-mcp.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
