confluence-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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. |
| 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
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.
Both tools use the same confluence_ prefix followed by a clear verb-noun pattern (get_point, parse_html). The naming is consistent and predictable.
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.
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.