conf-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 0 of 2 tools tried
Contacts while installing and starting: nothing
Its tool definitions changed since version 1.6.0. If you approved the earlier ones, read them again.
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y conf-mcp@1.7.0
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
2 tools that take no input and look read-only were called once with nothing. 0 returned a result.
list_spaces | No usable answer tool reported an error: Failed to parse URL from /rest/api/space?limit=25 |
get_user | No usable answer tool reported an error: Provide either 'key' or 'username'. |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
get_page page_id, body_format, body_limit, body_start, save_to
Get full details of a Confluence page by its numeric content ID or by a pasted page URL (viewpage.action?pageId=..., /spaces/KEY/pages/ID/..., or /display/SPACE/Title)
create_page body, parent_page_id, space_key, title, body_format
Create a new Confluence page. Pass Markdown with body_format='markdown' (converted server-side), or raw Confluence storage format (XHTML) with the default body_format='storage'
update_page body, page_id, title, body_format
Update a Confluence page. This is a full replace and auto-increments the version. Pass Markdown with body_format='markdown' (converted server-side), or raw Confluence storage format (XHTML) with the default body_format='storage'; omit body/title to keep existing values
patch_page edits, new_string, old_string, page_id
Replace exact substrings in a Confluence page's storage-format body without resending the full body. Pass one old_string/new_string pair, or several in edits to change many spots in one version (applied in order; if any edit fails to match exactly once, nothing is written). Use for targeted edits to large pages where update_page's full-body replace is impractical.
delete_page page_id
Move a Confluence page to trash (recoverable). Does not permanently purge
12 more tools
delete_pages page_ids
Move several Confluence pages to trash (recoverable). Does not permanently purge. Pages are processed in order; a failure on one does not stop the rest, and the result lists each page's outcome
move_page page_id, parent_id
Move a Confluence page (with its children) under a new parent page, including a parent in another space. Content and title are kept; the version increments
move_pages page_ids, parent_id
Move several Confluence pages (each with its children) under the same new parent page, including a parent in another space. Pages are processed in order; a failure on one does not stop the rest, and the result lists each page's outcome
get_page_by_title space_key, title, body_format, body_limit, body_start, save_to
Get a Confluence page by its space key and exact title
search_pages cql, limit, start
Search Confluence content using CQL (Confluence Query Language)
list_spaces limit, space_key
List Confluence spaces, or fetch a single space by key
get_user key, username
Resolve a Confluence user's display name and profile from a userKey or username. Useful for turning a page's stored userkey (e.g. from a user mention/link) into a readable name.
add_comment body, page_id
Add a comment to a Confluence page. Body must be Confluence storage format (XHTML), not Markdown
get_comments page_id, start
Get comments on a Confluence page, 50 per call. When the result has _links.next, call again with start increased by 50
upload_attachment comment, file_name, file_path, overwrite, page_id
Attach a local file to a Confluence page. If an attachment with the same name exists, fails unless overwrite=true, which uploads it as a new version. Reference it in the body with <ac:image><ri:attachment ri:filename="..."/></ac:image> or an ac:link
list_attachments page_id
List the attachments of a Confluence page (name, size, media type, version, download link)
download_attachment dest_path, filename, page_id
Download a page attachment (latest version) to a local file. Fails if dest_path already exists
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | not stated |
| Source | github.com/ameforge/atlassian-mcp |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-QlusyrXAZ7O5PBRL2eCtWL0Zpiuv5xKsbfnBskklegFbXwtvJ+A24tCy+wMZc4ZzZVB3NmAnsH2igPvAxhHwRw== |
Versions reported
| Version | Run | Result | Tools |
|---|---|---|---|
| 1.7.0 | 2026-11-16 | Starts with no setup | 17 |
| 1.6.0 | 2026-11-12 | Starts with no setup | 15 |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/conf-mcp)
New version out? Ask for a fresh report.