SignalKit Connector for Claude

Ask Claude about your brand's AI visibility, add prompts, read past reports, see who's beating you in AI answers — all from inside the chat. Generating a new report and suggesting prompts stay in the dashboard.

Install (Claude.ai + Claude Desktop)

Open Claude → Settings → Connectors → Add custom connector.
Paste this URL:
```
https://app.signalkit.ai/api/mcp
```
Click Connect. Claude will redirect you to sign in to SignalKit (via Clerk). Approve, and you'll bounce back to Claude with the connector installed.
Try it: ask Claude "How is my brand doing in AI search this week?"

Auth

SignalKit's MCP server speaks OAuth 2.0 with Dynamic Client Registration (RFC 7591). The discovery endpoint is:

https://signalkit.ai/.well-known/oauth-authorization-server

For local testing / CI you can also use a SignalKit API key:

Authorization: Bearer sk_live_…

Generate a key from account / API keys.

Tools

The connector exposes 20 tools. Each one is auto-bound to your default project unless you pass a projectId arg.

Tool	What it does	Status
`list_projects`	List your projects	Live
`list_brands`	Tracked brands with visibility / mentions / sentiment	Live
`list_prompts`	Tracked prompts and query configuration; use list_results for measurements	Live
`get_overview`	Dashboard overview + competitor leaderboard	Live
`list_alerts`	Recent visibility/sentiment/position alerts	Live
`create_project`	New project for a new brand	Live
`add_brand`	Track a brand (typically a competitor)	Live
`delete_brand`	Stop tracking a brand	Live
`add_prompt`	Add a prompt to run against LLMs	Live
`delete_prompt`	Remove a prompt	Live
`suggest_prompts`	AI-generated prompt suggestions — use the dashboard's Prompts → Suggest instead	Not via MCP
`run_prompt_now`	Run a prompt across its configured platforms immediately	Live
`list_results`	Raw LLM responses with mentions and citations	Live
`list_sources`	URLs cited by LLMs, ranked by citation count	Live
`mark_alert_read`	Mark an alert as read	Live
`list_reports`	Previously generated reports	Live
`generate_report`	Generate a CSV / JSON / PDF report — use the dashboard's Reports tab instead	Not via MCP
`get_billing`	Active prompt count, monthly cost, balance	Live
`get_settings`	Read stored notification settings	Live
`update_settings`	Update stored notification settings	Live

Programmatic discovery

The connector advertises a standard MCP server card at /.well-known/mcp/server-card.json with tool names, OAuth endpoints, and capability flags. Anthropic's marketplace reads this card; other MCP clients can too.

Example session (raw JSON-RPC)

For curl-driven testing, the streamable-HTTP endpoint takes a JSON-RPC request and returns a JSON-RPC response:

# Initialize
curl -sX POST https://app.signalkit.ai/api/mcp \
  -H "Authorization: Bearer sk_live_…" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'

# List tools
curl -sX POST https://app.signalkit.ai/api/mcp \
  -H "Authorization: Bearer sk_live_…" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list"}'

# Call a tool
curl -sX POST https://app.signalkit.ai/api/mcp \
  -H "Authorization: Bearer sk_live_…" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"get_overview","arguments":{}}}'

Support

Bug reports + feature requests: [email protected].