MCP Server Documentation

Connect your AI clients to search and query your Adviserry boards using the Model Context Protocol (MCP).

Quick Setup

To connect your AI client to Adviserry, you need your MCP token:

Log in to Adviserry Boards
Go to Settings and find the MCP Server Access section
Copy your personal MCP token

Your token authenticates requests via the Authorization: Bearer <token> header. Keep it secure.

Choose your AI client and follow the setup instructions:

Claude Desktop Configuration

Add this to your claude_desktop_config.json

{
  "mcpServers": {
    "adviserry": {
      "url": "https://www.adviserry.com/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_MCP_TOKEN"
      }
    }
  }
}

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Restart Claude Desktop after saving changes.

Available Tools

The Adviserry MCP server exposes 10 tools. Your AI client will discover these automatically once connected.

search_newsletters

Search through the user's newsletter knowledge base for relevant content. Use this to find information, quotes, or insights from newsletters the user has subscribed to.

Parameter	Type	Required	Description
`query`	string	Yes	The search query to find relevant newsletter content
`board_name`	string	No	Optional: Filter by a specific board name (e.g., 'Marketing', 'Tech')
`limit`	string	No	Maximum number of results to return (default: 5, max: 10)

list_boards

List all the user's advisory boards and the newsletters in each board.

No parameters required.

get_recent_issues

Get the most recent newsletter issues from a specific board or all boards.

Parameter	Type	Required	Description
`board_name`	string	No	Optional: Filter by a specific board name
`days`	string	No	Number of days to look back (default: 7, max: 30)
`limit`	string	No	Maximum number of issues to return (default: 10, max: 20)

get_newsletter_summary

Get a summary of a specific newsletter issue by its ID.

Parameter	Type	Required	Description
`issue_id`	string	Yes	The ID of the newsletter issue to summarize

get_topics

Get the key topics covered across the user's newsletters, optionally filtered by board or time range.

Parameter	Type	Required	Description
`board_name`	string	No	Optional: Filter by a specific board name
`days`	string	No	Number of days to analyze (default: 30, max: 90)

search_context

Search through the user's uploaded documents and URLs for relevant content. Use this to find information from PDFs, Word docs, spreadsheets, presentations, or web pages the user has added as context.

Parameter	Type	Required	Description
`query`	string	Yes	The search query to find relevant uploaded content
`board_name`	string	No	Optional: Filter by a specific board name. Global uploads are always included.
`limit`	string	No	Maximum number of results to return (default: 5, max: 10)

get_insights

Get proactive insights generated by the user's advisory boards. Insights are AI-generated connections between content from different sources, trends, and action items relevant to what the user is working on.

Parameter	Type	Required	Description
`board_name`	string	No	Optional: Filter by a specific board name
`status`	stringunread \| read \| saved \| all	No	Filter by status: 'unread', 'read', 'saved', or 'all' (default: 'all')
`limit`	string	No	Maximum number of insights to return (default: 10, max: 20)

get_user_context

Get the user's advisor profile — their role, what they're currently working on, and challenges they're facing. This context is used by boards to generate personalized insights.

No parameters required.

get_analytics_summary

Get a pre-built analytics summary for Adviserry Boards or Labs. Returns: daily active users, conversion funnel stats, feature adoption counts (chat, MCP, insights, YouTube), and OpenAI cost breakdown by feature. Use this to understand how the product is performing.

Parameter	Type	Required	Description
`project`	stringboards \| labs	No	Which site to query: 'boards' (default, adviserry.com product) or 'labs' (labs.adviserry.com public site)
`days`	string	No	Lookback window in days (default: 7, max: 90)

query_analytics

Run a custom HogQL (SQL-like) query against PostHog event data for Adviserry Boards or Labs. Use for ad-hoc analysis beyond the standard summary. Events schema: event (string), timestamp (DateTime), person_id (UUID), properties (JSON). Key events: $pageview, chat_message_sent, mcp_tool_called, insight_generated, youtube_channel_added, subscription_started, llm_generation (with properties: feature, total_tokens, estimated_cost_usd).

Parameter	Type	Required	Description
`query`	string	Yes	HogQL query string. Example: SELECT event, count() FROM events WHERE timestamp > now() - interval 7 day GROUP BY event ORDER BY count() DESC LIMIT 20
`project`	stringboards \| labs	No	Which site to query: 'boards' (default) or 'labs'

Example Prompts

Once connected, you can ask your AI client questions like:

"Search my boards for recent advice on fundraising"
"What are the latest newsletters about AI from my Tech board?"
"Summarize this week's issues from all my boards"
"What topics have my newsletters been covering lately?"
"Search my uploaded documents for competitive analysis"
"Show me unread insights from my Marketing board"
"List all my boards and their sources"

Rate Limits

Detail	Value
Requests per hour	20
Reset interval	Every hour on the hour
Over-limit response	HTTP 429 with error message

Troubleshooting

Connection Failed

Verify your MCP token is correct (copy it fresh from Settings)
Make sure the endpoint URL is https://www.adviserry.com/api/mcp (with www. — the non-www URL redirects and may strip auth headers)
Ensure the Authorization header is formatted as Bearer YOUR_TOKEN
Restart your AI client after making config changes

Rate Limit Exceeded

Wait for the current hour to expire. Your limit resets automatically every hour on the hour.

Empty Results

Verify you have newsletters or YouTube channels added to your boards
Check that your Gmail account is connected and synced
Try broadening your search query

Token Not Working

If you recently regenerated your token, make sure to update your AI client config with the new token. The old token is immediately invalidated.

Security Best Practices

Never commit your MCP token to version control or share it publicly
Regenerate your token immediately if you suspect it has been compromised (Settings → MCP Server Access → Regenerate Token)
Always use header-based authentication to prevent token exposure in URLs, logs, or browser history
Keep your AI client updated for the latest security patches

Need help? Contact support