# Demandbase MCP connector

Connect Demandbase to Elaichi and your team can look up accounts, surface buying intent, pull company news and find contacts from Claude, ChatGPT, Cursor or Microsoft Copilot, with every request logged under the person who made it.

Source: https://elaichi.ai/connectors/demandbase/

## Facts

| | |
| --- | --- |
| Application | Demandbase |
| Category | Marketing Automation |
| AI tools | 59 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Demandbase is connected

- Which accounts are showing intent for cloud security this week?
- Brief me on Acme Corp before my 2pm call
- Find VP-level contacts at companies surging on data governance

## Connect Demandbase in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Demandbase.
2. Optionally set Share with, then press Connect.
3. Paste a Demandbase API key. One person generates a token in Demandbase and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Demandbase tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Demandbase MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Demandbase MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Demandbase MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Demandbase MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Demandbase MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Demandbase to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Demandbase tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Demandbase through Elaichi

### Brief yourself on an account before a call

Sales. Ask for a company's Demandbase profile, its recent news and the topics it has been researching, and walk into the meeting knowing what they care about.

### Find the right contacts at a hot account

Sales Development. Search Demandbase contacts at a company showing intent and get names and titles to reach out to this week.

### Spot accounts surging on your keywords

Marketing. Run a Demandbase intent search for the topics your campaign covers and see which companies are showing interest right now.

### Keep activity types tidy across campaigns

Marketing Operations. Create or rename activity types in Demandbase so engagement from a new channel is tracked the way the team expects.

### Export an account list for the next push

Revenue Operations. Start an export job for a Demandbase account list and hand the result to the people building sequences, without leaving the chat.

### Add a custom source and watch credit usage

Revenue Operations. Set up or update a custom source in Demandbase, map its fields, and check credit usage so the team stays within plan.

## Elaichi vs Zapier MCP vs Composio for Demandbase

All three can connect Demandbase to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Demandbase tools | Allow or restrict single Demandbase tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Demandbase call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Demandbase to Claude?

Two steps. In Elaichi, choose Demandbase and paste in your Demandbase API key; there is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in with your Elaichi account and Demandbase is ready to use.

### Does Demandbase work with ChatGPT and Cursor as well as Claude?

Yes. Once Demandbase is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect Demandbase once and every client picks it up.

### What can an AI agent actually do with my Demandbase data?

It can look up a company in Demandbase, search for accounts showing intent on a topic, pull recent company news, find contacts at an account, and start an export of an account list. It can also create or update activity types and custom sources, and check credit usage. Short, concrete asks such as "accounts surging on data governance this week" work better than long sentences.

### Does connecting Demandbase give the AI access to everything in my account?

No. Every request runs under the Demandbase access of the person who signed in, so the agent sees the companies, contacts and sources that person could already see. Elaichi can narrow that further with roles and restrictions, and it never widens it.

### Can my team share one Demandbase connection?

Yes. One person connects Demandbase in Elaichi and shares it with a team, and nobody else ever handles the API key. Each teammate still signs in to Elaichi as themselves, so the audit log names the person behind every search, export and update.

### Can I stop an agent from deleting or changing things in Demandbase?

Yes. Restrictions in Elaichi work per action, so you can restrict deleting a custom source or updating an activity type in Demandbase for a role or for one person. A restricted action still shows up in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to a Demandbase connection when someone leaves?

Offboarding that person in Elaichi ends their access to Demandbase at once. A connection they shared keeps working for everyone else on the team. If you disconnect Demandbase in Elaichi, it disappears from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client in one step.

### Does the Demandbase MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Demandbase is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Demandbase?

Yes. Both let Claude, ChatGPT or Cursor use Demandbase. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Demandbase call.

### How is Elaichi different from Composio for Demandbase?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Demandbase: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 59 Demandbase tools

Every tool below is callable through https://api.elaichi.ai/mcp once Demandbase is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Create a Demandbase activity type** (Create). Create New Activity Type. Create a new activity type on your Demandbase tenant.
- **Get single Demandbase activity type by ID** (Get). Activity Type Lookup. Retrieve details of an activity type for data import. Required: id.
- **List all Demandbase activity types** (List). List Activity Types. Get all activity types currently configured on your Demandbase tenant
- **Update a Demandbase activity type by ID** (Update). Update Activity Type. Update an existing activity type on your Demandbase tenant. Use the activity type ID in the URI (via PUT /activity_type/{activityTypeId} ). Required: id.
- **Create a Demandbase auth token** (Create). Exchange the connected API Key Set client ID and secret for a short-lived JWT access token (used internally by the connection; no input needed).
- **Create a Demandbase bulk job** (Create). Create a Bulk Data Retrieval Job. Overview Create and run asynchronous bulk jobs to retrieve company or contact data using entity IDs or search filters. This API is ideal for large data exports with a file-based CSV output. You can submit up to 10,000 entity IDs in a single request. The API initiates an asynchronous job and returns a jobId to track its status and retrieve results using the Job Status API. Required: jobType, jobName, fields, filters.
- **Get single Demandbase bulk job by ID** (Get). Get Bulk Job Status. Check the status of a bulk job using its unique job ID. This endpoint supports all bulk job types, including Company Fetch, Contact Fetch, and Match. Once the job completes successfully, the response will contain a signed resultsUrl for downloading the results. Required: id.
- **Get single Demandbase company by ID** (Get). Fetch company details. Use this endpoint to fetch detailed information about a single company, including name, location, phone number, revenue, employee count, industry classification, and social media links. You can optionally expand the response to include related data such as the company's family tree, competitors, installed technologies, and logos. Required: id.
- **Demandbase companies search** (Search). Search companies. Use this endpoint to search for companies based on a variety of attributes. You can search companies by name, website, ticker, location (city, state, country, ZIP), industry classification (NAICS, SIC), or attributes like fiscal year end, business structure, and fortune ranking.
- **Demandbase company intent search** (Search). Retrieve company intent data. Returns company intent signals filtered by company IDs, keyword set IDs, or keywords within a specified date range. You can also filter results by intent strength or the number of people researching. At least one of companyIds , keywordSetIds , or keywords is required. Requests that include only a date range return error 400-218 . When you provide multiple filters, the API combines them using AND logic. Required: startDate, endDate.
- **Get single Demandbase company logo by ID** (Get). Fetch company logo. Use this endpoint to fetch a company's logo in PNG format at the requested size. Supported sizes are 100, 200, or 400 pixels. If a logo in the specified size is not available, the API returns an error response. Required: company_id, id.
- **List all Demandbase company news** (List). Fetch company news by category. Use this endpoint to fetch recent news articles related to a specific company. You can filter articles by one or more news categories, such as acquisitions or leadership changes. Pagination is supported to control the number of results per request. Required: company_id, newsCategories.
- **List all Demandbase company news feed** (List). Fetch company news feed. Use this endpoint to return a paginated list of recent news articles for a specific company. Unlike the /news endpoint, this feed does not require specifying news categories. It provides a general stream of company-related articles. Required: company_id.
- **Get single Demandbase contact by ID** (Get). Fetch contact details. Use this endpoint to fetch detailed employment and personal information for a specific contact. Retrieve data such as job titles, phone numbers, job levels, salary ranges, social profiles, and education history. You can control the response using query parameters to include specific fields or additional related data. Required: id.
- **Demandbase contacts search** (Search). Search contacts. Use this endpoint to search for individuals at specific companies. You can filter contacts by details such as first name, last name, email, location, job title, job level, and job function. Company-level filters include company name, website, location, industry, size, and more. Additional parameters allow you to filter by quality score, email validation status, and phone requirements.
- **List all Demandbase credit usage** (List). Fetch Credit Usage details. Returns a summary of credit usage and entitlements for the specified API category. Required: apiProduct.
- **Get single Demandbase custom source field mapping by ID** (Get). Get field mappings. Returns the field mappings configured for the given source and object type. Returns 404 if no mappings have been configured yet for that object type; create them with the upsert endpoint before importing data. Required: source_id, id.
- **Update a Demandbase custom source field mapping by ID** (Update). Upsert field mappings. Creates or replaces the field mappings for the given source and object type. The full set of mappings in the request body replaces any existing mappings, so include every mapping you want to keep. Field mappings are required before you import data into a custom source. Include a mapping for External Account ID to crmId___e ; it is how imported records are matched to existing accounts. Required: source_id, id, fieldMappings.
- **Create a Demandbase custom source** (Create). Create a custom source. Creates a new custom source and returns it. A tenant can have at most 50 custom sources. After creating a source, define its field mappings before importing data into it. Required: name, description, priority.
- **Delete a Demandbase custom source by ID** (Delete). Delete a custom source. Deletes a custom source by its ID. Only custom sources can be deleted. Required: id.
- **Get single Demandbase custom source by ID** (Get). Get a custom source. Returns a single source by its ID. Required: id.
- **List all Demandbase custom sources** (List). List custom sources. Returns a paginated list of sources, optionally filtered by source group.
- **Update a Demandbase custom source by ID** (Update). Update a custom source. Updates an existing source by its ID and returns the updated resource. Required: id, name, description, priority.
- **Create a Demandbase export account list job** (Create). Create account list export job. Create a job to export all account lists or the account members of one or more specified account lists. Required: jobName.
- **List all Demandbase export fields** (List). Export fields. The Fields endpoint returns a list of all fields available for specific data export jobs. For campaign and creative export jobs, the query parameter adReportType is required. Required: entityType.
- **Create a Demandbase export job** (Create). Create export job (Account, Opportunity, Person, Activity, Campaign, and Creative). Creates a data export job for any supported entity type. Required: entityType, jobName, fields.
- **Get single Demandbase export job by ID** (Get). Check status of a data export job. Returns the current job status. Finished jobs include a download URL when a result file is available; download URLs are valid for 24 hours. Required: id.
- **List all Demandbase export jobs** (List). Returns a list of submitted export jobs. Returns export jobs submitted for the authenticated tenant. Use the query parameters to filter, sort, and paginate the results.
- **Create a Demandbase export person list job** (Create). Create person list export job. Create a job to export all person lists or the person members of one or more specified person lists. Required: jobName.
- **Get single Demandbase export reference by ID** (Get). Get reference data fields for an object. Returns the records for one supported reference object. Object-name matching is case-insensitive. Required: id.
- **List all Demandbase export references** (List). Get available reference objects. Returns the reference objects available through the Export API, including the endpoint for retrieving each object's data.
- **Demandbase import job data bulk update** (Import). Submit import data. This endpoint is used to submit the data file to an existing import job identified by the path parameter {id}. Submitting the data file triggers the asynchronous processing of the data. You can monitor the progress and final status of the data processing using the dedicated job status endpoint. Send the CSV file content as the raw request body. Required: job_id, file.
- **Create a Demandbase import job** (Create). Create an import job. Create a new job to perform a Data Import. This is prerequisite before posting a file with records to be imported. Required: dataImportName, entityType.
- **Get single Demandbase import job by ID** (Get). Job status. Use this endpoint to retrieve the current status and relevant details of a specific data import job. The job is identified by the unique path parameter {id} that was returned when the job was initially created. Required: id.
- **List all Demandbase import jobs** (List). Jobs list. Returns a list of import jobs. This provides an overview of all historical and current data import activities within the Demandbase platform.
- **List all Demandbase import sources** (List). Sources. Returns a list of eligible sources. Required: entity_type.
- **List all Demandbase keyword set keywords** (List). List the keywords of a keyword set. Returns one page of the keywords belonging to the given keyword set. totalCount is the number of keywords in the whole set, not in the returned page. A page beyond the last page returns 200 with an empty keywords array. A keyword set that does not exist, or belongs to another tenant, returns 404-106 — never 403 , so identifiers cannot be enumerated across tenants. Required: keyword_set_id.
- **List all Demandbase keyword set seed URLS** (List). List the seed URLs of a keyword set. Returns one page of the seed URLs belonging to the given keyword set. totalCount is the number of seed URLs in the whole set, not in the returned page. A page beyond the last page returns 200 with an empty seedUrls array. A keyword set that does not exist, or belongs to another tenant, returns 404-106 — never 403 , so identifiers cannot be enumerated across tenants. Required: keyword_set_id.
- **Create a Demandbase keyword set** (Create). Create a keyword set. Creates a keyword set for your tenant together with its initial keywords and optional seed URLs. name and keywords are required. keywords may be an empty array — a set is allowed to start empty — but the property itself must be present. Keywords are trimmed and then de-duplicated case-insensitively, so the created set may hold fewer keywords than were submitted. Required: name, keywords.
- **List all Demandbase keyword sets** (List). List keyword sets. Returns one page of keyword-set metadata for your tenant, optionally filtered, sorted and paginated. List items never include keywords or seedUrls . Read those through the /keyword-sets/{keywordSetId}/keywords and /keyword-sets/{keywordSetId}/seed-urls subresources, each of which paginates independently. This is also how a single keyword set's metadata is read: GET /keyword-sets?id=9427 .
- **Update a Demandbase keyword set by ID** (Update). Update a keyword set. Applies a partial update. Every property is optional and any property omitted retains its stored value, but at least one must be supplied — an absent, empty or wholly unrecognized body is rejected with 400-242 . Required: id.
- **Create a Demandbase match job** (Create). Match Companies and Contacts in Bulk. Use this endpoint to enrich company and contact records in bulk using a CSV file upload. Each row in the file represents one enrichment request and must match the supported field structure. This endpoint supports up to 10,000 records per job. Send the CSV file content as the raw request body. Required: jobName, file.
- **Create a Demandbase match** (Create). Match companies and contact. This endpoint matches companies and contacts against Demandbase's database based on provided firmographic and contact details. This endpoint supports batch matching by accepting an array of match requests. Each object in the requests array must include a unique id and a useful combination of attributes for matching. Required: requests.
- **Get single Demandbase reference datum by ID** (Get). Get reference data for an object. Returns tenant-specific reference values for the requested object. This B2B API route is backed by the Data Export API reference service and accepts B2B API credentials. Object names are case-insensitive. Required: id.
- **Get single Demandbase subscription alert by ID** (Get). Retrieve a Specific Subscription Alert. Retrieve detailed alert updates for a specific subscription using its subscription ID and alert ID. Use List Subscription Alerts API to fetch latest alerts. This endpoint returns the specific fields or news categories that triggered the alert, depending on the type of subscription: - company : Returns a list of company IDs and the fields that changed (e.g., name, address). Required: subscription_id, id.
- **List all Demandbase subscription alerts** (List). List Subscription Alerts. Retrieve a paginated list of alerts generated for the specified subscription ID. Each alert includes: - alertId : unique identifier for the alert - createdAt : timestamp of when the alert was generated Results are sorted in descending order of createdAt (most recent first). Required: subscription_id.
- **List all Demandbase subscription entity IDS** (List). Get Subscription Entity IDs. Retrieve all entity IDs (company or dbPerson) associated with a given subscription. The response is paginated and depends on the type of subscription: - For "company" or "companyFamilyTree" subscriptions, it returns Company IDs. - For "dbPerson" subscriptions, it returns Demandbase Person IDs. Required: subscription_id.
- **Demandbase subscription jobs bulk update** (Update). Update an Existing Subscription. Use this API to update an existing subscription. You must provide both the subscriptionId and subscriptionType to identify which subscription you want to modify. This endpoint supports partial and full updates, including: - Replacing all associated entity IDs with the subscription (e.g., company IDs or dbPerson IDs). - Incrementally adding or removing entity IDs in the subscription.
- **Create a Demandbase subscription job** (Create). Create a New Subscription. Use this endpoint to create a subscription for monitoring updates to companies or DB Person records. Subscriptions allow you to receive change alerts via webhook and access historical alerts via API. Each subscription is processed asynchronously. A jobId is returned on submission. Upon completion, the job will return a subscriptionId which can be used to fetch alerts or manage the subscription.
- **Get single Demandbase subscription job by ID** (Get). Check Subscription Job Status. Retrieve the current status of a bulk subscription job using its unique job ID. After you submit a create or update subscription job request, you’ll receive a job ID. This endpoint allows you to monitor that job’s progress and determine whether it has completed successfully. If the job completes, the response will include the generated subscriptionId—which you can use to manage the subscription. Required: id.
- ...and 9 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
