Skip to main content
Glama
confluence-mcp-server

confluence-mcp-server

by azamlerc

confluence-mcp-server

MCP server for fetching and parsing confluence.org point pages.

Tools

confluence_get_point

Fetches and parses a point directly from confluence.org.

Warning: confluence.org can be very slow (10+ seconds per page). The tool has a 30s timeout.

Parameters:

  • lat — signed integer latitude (e.g. 57, -33)

  • lon — signed integer longitude (e.g. 24, -3)

confluence_parse_html

Parses raw HTML you've already fetched yourself (e.g. via browser automation or curl). Useful for avoiding the slow server by batching fetches separately.

Parameters:

  • html — raw HTML string

  • lat — integer latitude

  • lon — integer longitude

Related MCP server: geolabel-mcp

Returned data

Both tools return a human-readable summary and a JSON object:

{
  lat: number;
  lon: number;
  prefix: string;            // "57°N 24°E"
  country: string;           // "Latvia"
  region?: string;           // "Euskadi" (not always present)
  locationDescription: string; // "4.8 km (3.0 miles) SW of Bolderāja, Rīgas, Latvia"
  distanceKm: number;        // 4.8
  direction: string;         // "SW"
  nearestPlace: string;      // "Bolderāja"
  altitudeM?: number;        // 19
  visitCount: number;        // 12
  notes?: string;            // contents of the Notes section, if present
}

The nearestPlace field is what you'll usually want to use as the entity name in the database — but confirm with Andrew since it's subjective (sometimes a better-known nearby town is preferable to the literally closest village).

Setup

npm install
npm run build

Claude Desktop config

{
  "mcpServers": {
    "confluence": {
      "command": "node",
      "args": ["/Users/andrewzc/Projects/confluence-mcp-server/dist/index.js"]
    }
  }
}

confluence-mcp-server

Available Tools

2 tools
confluence_get_pointA

Fetch and parse a confluence.org point page by latitude and longitude. Returns structured data about the point including country, nearest place, distance, visit count, and any notes. Warning: confluence.org can be slow (10+ seconds), so this tool has a 30s timeout.

Inputs: lat (required), lon (required).

confluence_parse_htmlA

Parse raw HTML from a confluence.org point page. Useful when you've fetched the HTML yourself (e.g. via browser). Returns the same structured data as confluence_get_point.

Inputs: lat (required), lon (required), html (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 2 tools

    Disambiguation5/5

    Both tools return the same structured data, but their inputs are clearly distinct (raw HTML vs lat/lon), and the descriptions explicitly state when to use each. There is no realistic selection ambiguity.

    Naming Consistency5/5

    Both tools use the same confluence_ prefix followed by a clear verb-noun pattern (get_point, parse_html). The naming is consistent and predictable.

    Tool Count4/5

    At two tools this is below the typical 3-15 range, but for the narrow read-only domain of fetching and parsing Confluence point pages, it is a reasonable minimal set without redundant tools.

    Completeness5/5

    The server covers the full implied workflow: either fetch a point by coordinates or parse already-fetched HTML into structured point data. There are no missing read operations or dead-end workflows for this domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers