Connect your AI Agents to Crustdata in minutes
Available tools
autocomplete_person_field
Autocomplete person database field values. Returns suggestions for a given field and query. No credits consumed. Use before search_people_in_db to discover valid filter values.
autocomplete_company_field
Autocomplete company database field values. Returns suggestions for a given field and query. No credits consumed. Use before screen_companies to discover valid filter values.
autocomplete_filters
Autocomplete LinkedIn filter values for region, industry, title, or school. No credits consumed. Use before search_people or search_companies to discover valid filter values.
identify_company
Identify a company by name, website, LinkedIn URL, Crunchbase URL, or Crustdata ID. Returns matching companies with IDs and profile URLs. No credits consumed. Use this to resolve company identifiers before enrichment or people search.
enrich_company
Enrich companies by domain. Returns firmographics, headcount, funding, revenue, and more. Pass comma-separated domains for multiple companies.
screen_companies
Screen companies via companydb/search. Filter fields: company_name, hq_country, employee_metrics.latest_count, total_funding_usd. Operators: =, !=, in, not_in, >, (.) fuzzy, [.] exact token. Use cursor for next page.
search_companies
Search companies in real-time using typed filters. Filter types: COMPANY_HEADCOUNT, REGION, INDUSTRY, ANNUAL_REVENUE, KEYWORD, etc. 25 results per page.
search_job_listings
Search job listings with filters. Filter columns: company_name, company_id, title, location, date_posted, url, seniority_level, employment_type. Operators: =, !=, =>, =100 results. 1 credit per company.
get_company_linkedin_posts
Get LinkedIn posts for a company. Provide one company identifier (name, domain, ID, or LinkedIn URL) OR a specific post URL. Returns post text, reactions, comments, shares. Latency: 30-60 seconds.
search_linkedin_posts_by_keyword
Search LinkedIn posts by keyword. Filter by date range, content type, and sort by relevance or date. Returns matching posts with reactions and comments.
enrich_person
Enrich person profiles by LinkedIn URL. Returns employment history, education, skills, contact info. Pass comma-separated URLs for multiple people.
search_people
Search people in real-time using typed filters. Filter types: CURRENT_TITLE, CURRENT_COMPANY, SENIORITY_LEVEL, REGION, INDUSTRY, etc. 25 results per page.
search_people_in_db
Search people in Crustdata's database with field-level filters. Filter by current_employers.title, region, years_of_experience_raw, headline, education, skills, etc. Supports AND/OR logic, fuzzy (.) and substring [.] matching, geo_distance radius search. Cursor-based pagination, max 1000 results per request.
get_social_posts
Get LinkedIn social posts for a person. Returns post text, reactions, comments, shares. 20 posts per page. Latency: 30-60 seconds.
get_remaining_credits
Get the remaining API credits for the authenticated Crustdata account. No credits consumed. Use to check balance before running credit-consuming operations.
validate_credential
Validate Crustdata credentials. Verifies credentials during setup.
create_watch
Create a new watch to track events like job postings. Specify event type, filters for events/leads/accounts, a webhook URL for notifications, frequency in days, and an expiration date. Returns the created watch with its ID and status.
update_watch
Update an existing watch by ID. Can change status to 'paused' or 'active', update the webhook URL, modify event filters (lead watches only), or adjust max notifications per run. At least one field must be provided.
get_watch
Get details of a specific watch by its ID. Returns the watch configuration including event type, filters, webhook URL, frequency, status, and expiration date.
list_watches
List all watches for the authenticated account. Returns all active and paused watches with their configurations.
web_search
Search the web using Crustdata's search API. Supports news, web, scholar articles, AI, and social sources. Filter by geolocation, site, and date range. 1 credit per 10 results.
web_fetch
Fetch web page content by URLs. Returns page title and HTML content for each URL. Max 10 URLs per request. 1 credit per URL.
How to set up Merge Agent Handler
In an mcp.json file, add the configuration below, and restart Cursor.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5 "headers": {
6 "Authorization": "Bearer yMt*****"
7 }
8 }
9 }
10}
11Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.
Make sure Claude is using the Node v20+.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "yMt*****"
14 }
15 }
16 }
17}Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "<ah-production-access-key>"
14 }
15 }
16 }
17 }In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".
You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.
Learn more in the official documentation ↗
1{
2 "inputs": [
3 {
4 "type": "promptString",
5 "id": "agent-handler-auth",
6 "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7 "password": true
8 }
9 ],
10 "servers": {
11 "agent-handler": {
12 "type": "stdio",
13 "command": "npx",
14 "args": [
15 "-y",
16 "mcp-remote@latest",
17 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18 "--header",
19 "Authorization: Bearer ${input:agent-handler-auth}"
20 ]
21 }
22 }
23}FAQs on using Merge's Crustdata MCP server
FAQs on using Merge's Crustdata MCP server
Ready to try it out?
Whether you're an engineer experimenting with agents or a product manager looking to add tools, you can get started for free now
