Get Given Recommendations
/get-given-recommendationsRetrieve recommendations that a user has written for others. Writing recommendations reveals a person's professional network, generosity, and the types of professionals they vouch for — useful for mapping professional relationships.
Call it over REST
Authenticate with a bearer token against https://api.superagnt.com. Swap the placeholders for your key and parameter values.
curl -s "https://api.superagnt.com/get-given-recommendations?username=<username>" \
-H "Authorization: Bearer <YOUR_AGNTDATA_API_KEY>"Copy-paste prompt
Paste this into a coding agent. It connects the superagnt MCP server, finds the tool data_linkedin_get_given_recommendations, and runs a first call — with the REST fallback if MCP is unavailable.
You are wiring up the superagnt "LinkedIn" API to use this endpoint: Get Given Recommendations.
1. CONNECT over MCP (preferred). No token to paste either way.
On Claude (claude.ai, the desktop app, or Claude Code signed in with a Claude
account), the server is a connector: give the user this link, they click Add
and approve:
https://claude.ai/customize/connectors/yours?modal=add-custom-connector&connectorName=superagnt&connectorUrl=https%3A%2F%2Fmcp.superagnt.com%2Fmcp&open_in_browser=1
Any other MCP client (or Claude Code signed in with an API key): add the server
and let the client run the browser sign-in:
claude mcp add --scope user --transport http superagnt https://mcp.superagnt.com/mcp
claude mcp login superagnt
MCP endpoint: https://mcp.superagnt.com/mcp
After connecting, the tool you want is named exactly:
data_linkedin_get_given_recommendations
Call agnt_tools_search or agnt_tools_list_enabled to confirm it is available.
2. REST fallback (if you are not using MCP):
GET https://api.superagnt.com/get-given-recommendations
Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
Required parameters:
- username (string, required)
Optional parameters:
- start (string, optional)
3. COST & KEY. Each successful call costs $0.009 in credits. Only successful calls are charged.
Get a superagnt API key at https://app.superagnt.com.
4. TEST. Connect the server (or set the key), discover the tool
(data_linkedin_get_given_recommendations), run one minimal call with just the required parameters,
and report back the shape of the JSON response (top-level fields).
Reference (machine-readable variant): https://www.superagnt.com/docs/apis/social/linkedin/endpoints/Get_Given_Recommendations.md{
"name": "get_given_recommendations",
"description": "To scrape all recommendations from a profile, increase the start value to +100 for each request until you reach the total recommendations count. You can find the total recommendations count in the response",
"parameters": {
"type": "object",
"properties": {
"start": {
"type": "string",
"description": "query parameter",
"default": "0"
},
"username": {
"type": "string",
"description": "query parameter",
"default": "ryanroslansky"
}
},
"required": [
"username"
]
}
}| Name | In | Type | Required | Description |
|---|---|---|---|---|
start | query | string | optional | |
username | query | string | required |
OK
{
"type": "object",
"properties": {
"success": {
"type": "boolean"
},
"message": {
"type": "string"
},
"data": {
"type": "array",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string"
},
"created": {
"type": "integer"
},
"lastModified": {
"type": "integer"
},
"relationship": {
"type": "string"
},
"recommendee": {
"type": "object",
"properties": {
"firstName": {
"type": "string"
},
"lastName": {
"type": "string"
},
"occupation": {
"type": "string"
},
"username": {
"type": "string"
}
}
}
}
}
},
"total": {
"type": "integer"
}
}
}Credits are deducted from your superagnt balance on each successful call. Failed requests (4xx/5xx) are not charged.
Get started at app.superagnt.com.
start calling
Point your client at https://mcp.superagnt.com/mcp and your agent has this endpoint, plus every other source on one balance.