MCP Integration - AI-Powered Research Access
Last updated by Administrator on 02/01/2026
The Model Context Protocol (MCP) allows AI assistants like Claude to directly access OppIntell's opposition research database. This enables real-time queries for candidate information, voting records, controversies, and more.
Instead of relying on potentially outdated training data, AI assistants can query our live database for accurate, up-to-date political research. This eliminates hallucinations and provides verifiable, sourced information.
MCP Server Endpoint:
https://oppintell.com/functions/v1/mcp-serverAvailable MCP Tools
search_candidates
Search for candidates by name, state, or race type.
get_candidate_profile
Get detailed profile including summary, finance data, and status.
get_candidate_controversies
Get documented controversies and concerns for a candidate.
get_candidate_voting_record
Get voting history and legislative record.
get_candidate_quotes
Get notable quotes and public statements.
get_candidate_issues
Get key policy positions and issues.
list_races
List all races by type (House, Senate, Governor).
get_receipt Free tier
Get the citable provenance for a published claim -- content SHA-256, span locator, source URL, capture timestamp, and supersession status. Provenance only, never claim text or the full source.
Free Tier & Attribution
A free, read-only, rate-limited API key gives any AI agent citable access to the same public research corpus this server has always served -- no payment, no account. Each key has a hard per-minute and per-day request cap, and free-tier responses are watermarked with an attribution notice. Attribution to OppIntell with a link to the canonical source is required when citing or redistributing free-tier data. Higher-volume or attribution-optional access is available on a separate commercial rate card -- contact us for details.
Claude Desktop Setup
Setup Instructions
- Open Claude Desktop: Launch the Claude desktop application
- Access Settings: Click the menu icon and go to Settings → Developer
- Edit Config: Click "Edit Config" to open the configuration file
- Add MCP Server: Add the following configuration:
{ "mcpServers": { "oppintell": { "url": "https://oppintell.com/functions/v1/mcp-server", "headers": { "x-api-key": "YOUR_OPPINTELL_API_KEY" } } } } - Restart Claude: Save the file and restart Claude Desktop
Cursor IDE Setup
Setup Instructions
- Open Cursor Settings: Go to Cursor Settings → MCP
- Add Server: Click "Add new global MCP server"
- Configure: Enter the following:
{ "mcpServers": { "oppintell": { "url": "https://oppintell.com/functions/v1/mcp-server", "headers": { "x-api-key": "YOUR_OPPINTELL_API_KEY" } } } } - Enable: Toggle the server to enabled state
Testing the Integration
You can test the MCP server using the MCP Inspector tool and an OppIntell API key:
npx @modelcontextprotocol/inspectorOnce connected, try asking Claude or your AI assistant questions like:
- "Search for candidates in Arizona by party"
- "What are the controversies for [candidate name]?"
- "Show me the voting record for [candidate name]"
- "List all Senate races"
Need Help?
If you encounter any issues setting up the MCP integration, reach out to our support team.
Contact Support