Connect your AI Agents to Sprout Social in minutes
Available tools
get_profile_analytics
Get daily profile performance analytics for one or more profiles over a date range. Returns a comprehensive metric set by default (followers, impressions, engagements, reactions, clicks, video views, etc.); pass metrics to narrow it. Provide customer_profile_ids (from list_profiles) and start_date/end_date (YYYY-MM-DD, max 1 year). Metrics vary by network.
list_posts
List sent posts with lifetime performance metrics for one or more profiles over a created-time window. Returns a comprehensive default metric set plus post details; pass metrics for gated ones like lifetime.net_sentiment_score. Provide customer_profile_ids (from list_profiles) and start_date/end_date (date or ISO datetime). Also the only way to fetch individual posts.
list_messages
List inbox messages (comments, mentions, DMs, etc.) for a profile. Requires customer_profile_id (from list_profiles). Defaults to the last 7 days when no date range or message_id is given. To filter by date pass start_date AND end_date together (max 1-week window); passing only one errors. Optional message_id, tag_id, post_type. Forward-only pagination: pass page_info.cursor back as 'cursor'.
list_cases
List Care cases. Filter by a date range (pass start_date AND end_date together, max 1-week window; passing only one errors) or look up a single case_id, plus optional queue_id, status, priority, type, assigned_to, or tag_id. Forward-only pagination: pass page_info.cursor back as 'cursor' for the next page.
list_topic_messages
List individual messages (mentions) inside a Listening topic over a date range. Provide topic_id (from list_topics) and start_date/end_date (YYYY-MM-DD or ISO datetime). Sprout requires a network filter on this endpoint; pass networks (e.g. ['twitter']) if you get a filter error. Returns a default set of message fields; override with fields.
get_topic_metrics
Get aggregated metrics for a Listening topic over a date range (volume, authors, sentiment, engagements, etc.), optionally bucketed by dimensions (e.g. created_time.by(day), network, sentiment). Defaults to volume and total_unique_authors; pass metrics for more. Provide topic_id (from list_topics) and start_date/end_date. Returns all results in one response.
list_clients
List the Sprout Social accounts (customers) your credentials can access, with their customer_id and name. Most credentials map to one account. Use a customer_id from here only if you manage multiple accounts.
list_profiles
List the social profiles connected to the account (Twitter/X, Facebook, Instagram, LinkedIn, etc.) with their customer_profile_id, network, and handle. Use the customer_profile_id for analytics, messages, and posting.
list_groups
List the groups in the account (group_id and name). Groups organize profiles and are needed when creating posts.
list_users
List the users in the account (id, name, email).
list_teams
List the teams in the account (id, name, description).
list_queues
List the Care case queues in the account (id, name, description, associated teams).
list_topics
List the Listening topics in the account (id, name, type, description).
list_tags
List the message tags (labels and campaigns) in the account, including archived ones (tag_id, text, type, active).
upload_media
Upload an image or video to Sprout from a public URL and get a media_id to attach to a post. content_type (e.g. image/jpeg) is inferred from the URL extension if omitted. Tip: create_post can take media_urls directly, so you usually don't need this tool.
create_post
Create a DRAFT post on one or more profiles. Provide customer_profile_ids (from list_profiles) and text and/or media_urls (public image/video URLs, uploaded and attached automatically). Optionally schedule via scheduled_times (ISO 8601 UTC) and apply tag_ids. group_id is auto-resolved for single-group accounts. Note: the API only creates drafts, and some networks (e.g. Instagram) require media.
get_post
Get a publishing (draft) post by its publishing_post_id (returned from create_post). Returns the post's text, media, schedule, and metadata.
validate_credential
Validate Sprout Social credentials by fetching the accessible account. Returns success status and a message. Use this to confirm a connection works.
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 Sprout Social MCP server
FAQs on using Merge's Sprout Social MCP server
What is a Sprout Social MCP?
A Sprout Social MCP is a server that exposes Sprout Social's publishing, engagement, and analytics functionality to your agents as tools. Your agents can use them to draft and schedule posts, pull engagement metrics, read inbox messages, generate analytics reports, and more.
Sprout Social offers an official MCP server, but you can also use one from a third-party platform, like Merge Agent Handler.
How can I use the Sprout Social MCP server?
The use cases naturally depend on the agent you've built, but here are a few common ones:
- Content scheduling from a brief: an agent can take an approved campaign brief, draft platform-specific posts, and schedule them in Sprout Social across the right profiles
- Inbox triage: an agent can scan incoming messages, classify them by intent, and route product complaints to a support queue while flagging sales leads for the right team
- Performance reporting: an agent can pull engagement and reach metrics for the past week and assemble a summary for a marketing lead, highlighting the top and worst performing posts
- Cross-tool campaign coordination: when a post hits an engagement threshold, an agent can log the result in your CRM or notify the team so they can follow up
What are popular tools for Sprout Social's MCP server?
Here are some of the most commonly used tools:
create_draft_post: creates a draft post for one or more profiles. Useful for agents that turn approved copy into ready-to-review content
schedule_post: schedules a post to publish at a set time. Call this when an agent programs a content calendar
get_analytics: returns engagement, reach, and impression metrics over a date range. Use this when an agent builds a performance report
list_messages: returns messages from the social inbox filtered by profile or status. Good for workflows that triage inbound conversations
list_profiles: returns the connected social profiles and their details. Helpful when an agent needs to target the right account before publishing
publish_post: publishes a post immediately to the selected profiles. Useful for agents that handle time-sensitive, pre-approved content
What makes Merge Agent Handler's Sprout Social MCP server better than alternative Sprout Social MCP servers?
A few things make Merge Agent Handler's Sprout Social MCP server the stronger choice over building one or using an alternative:
- Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Sprout Social, this means customer direct messages and the personal data inside inbox conversations can be redacted before the agent sees them
- Managed authentication and credentials: Merge stores and refreshes Sprout Social credentials on your behalf. You never expose raw API keys or OAuth tokens to an agent or manage rotation manually
- Real-time observability and audit trail: Every tool call made against Sprout Social is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly what an agent published or read from the inbox without setting up logging yourself
- Tool Packs and controlled access: Tool Packs let you bundle specific Sprout Social tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more
How can I start using Merge Agent Handler's Sprout Social MCP server?
You can take the following steps:
1. Create or log into your Merge Agent Handler account.
2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.
3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp, then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.
4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Sprout Social and complete the auth flow. Merge stores and manages the credentials going forward.
5. Open a Claude Code session and start querying Sprout Social data directly. The first time you use a Sprout Social tool, a Magic Link may appear to complete connector authentication.
If you want to connect Merge Agent Handler's Sprout Social MCP with internal or customer-facing agentic products, you can follow the steps in our docs.
Can employees use Merge Agent Handler to connect their AI tools to Sprout Social?
Yes, Agent Handler for Employees lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Sprout Social without bypassing IT governance.
Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Agent Handler and gets individual credentials tied to their identity. A social manager can ask their AI to schedule a post, pull last week's engagement, or triage the inbox, all within the permissions IT has defined.
IT also provisions access by role or group via SCIM. A social media manager, for example, gets Sprout Social access to schedule posts and pull engagement metrics, Canva to source creative, and Slack to route approvals; while a support agent gets Sprout Social access to triage inbound messages, Zendesk to open tickets, and Salesforce to check customer history.
Every tool call an employee's AI makes to Sprout Social is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.
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
