Rolli MCP
UnclaimedMCP server for Rolli IQ — social media search and analytics
Set up this server
01 / Choose your client
02 / Before you connect
Authentication is not specified. Check the project instructions before connecting.
Project instructions03 / Add the configuration
claude mcp add --transport stdio 'rolli-mcp' -- 'npx' '-y' '@rolli/mcp'04 / Check it in your client
Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.
More in Search & Web
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
30 of 30 tools
Documented tools (30)
From project documentation. A server handshake does not verify each tool’s description or behavior.
cancel_agent_run
Cancel a pending or running Rolli Agent run
create_agent_schedule
Create a recurring Rolli Agent report (daily/weekly/monthly/once)
delete_agent_run
Soft-delete a completed or failed Rolli Agent run
delete_agent_schedule
Permanently delete a Rolli Agent schedule
expert_search
Find experts matching a natural-language query and return results when complete
get_agent_run
Get a Rolli Agent run by ID (progress while running, full report when complete)
get_agent_schedule
Get a Rolli Agent schedule with its 10 most recent runs
get_expert_search
Get expert search results (recommended experts with AI-generated match summaries)
get_integration_setup
Get current integration settings (webhook URL, name)
get_keyword_search
Get keyword search results (status, analytics, posts)
get_keyword_search_posts
Get raw posts from a keyword search
get_topic_tree
Get conversation topic tree for a keyword search
get_usage
Get API usage data and per-user breakdowns
get_user_search
Get user search results (profile, metrics, content analysis)
get_user_search_posts
Get raw posts from a user search
keyword_search
Create a keyword/hashtag search and return results when complete
list_agent_runs
List Rolli Agent runs (AI-driven social intelligence investigations)
list_agent_schedule_runs
List the full execution history of a Rolli Agent schedule
list_agent_schedules
List Rolli Agent scheduled reports
list_expert_searches
List all expert searches, filtered by status
list_keyword_searches
List all keyword searches, filtered by status
list_user_searches
List all user searches, filtered by status
pause_agent_schedule
Pause a Rolli Agent schedule
rerun_agent_run
Retry a failed, waiting, or stuck Rolli Agent run
resume_agent_schedule
Resume a paused Rolli Agent schedule
start_agent_run
Start a Rolli Agent investigation and return the markdown report when complete
update_agent_run
Pin or rename a Rolli Agent run
update_agent_schedule
Update a Rolli Agent schedule
update_integration_setup
Set the webhook URL for search completion notifications
user_search
Create a user profile search and return results when complete
Tool change history
FAQ
Questions about Rolli MCP Server
- How do I connect Rolli MCP Server to Claude?
- Run `claude mcp add rolli-mcp -- npx -y @rolli/mcp` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
- Is Rolli MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Rolli MCP Server do?
- Rolli MCP Server documents 30 tools to the agent, including cancel_agent_run, create_agent_schedule, delete_agent_run. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.