Read-only MCP server for self-hosted Confluence that lets AI agents search pages, fetch content, and navigate page trees via the REST API
Detailed security scan evidence is not public for this MCP yet. Public identity, registry metadata, and independently observed protocol inventory remain available.
Installation and connection instructions are shown only when supported by retained package, repository, or endpoint evidence.
Version 0.1.0 declares 1 executable entrypoint.
npm install --save-exact confluence-http-api-mcp@0.1.0npx -y -p confluence-http-api-mcp@0.1.0 confluence-http-api-mcp{
"mcpServers": {
"confluence-http-api-mcp": {
"command": "npx",
"args": [
"-y",
"-p",
"confluence-http-api-mcp@0.1.0",
"confluence-http-api-mcp"
]
}
}
}| Canonical slug | confluence-http-api-mcp-e4cafa57 | Deployment | Local Only |
|---|---|---|---|
| Canonical package | npm:confluence-http-api-mcp | Repository | rkorablin/confluence-http-api-mcp |
| First published | — | Latest release | — |
| Last security verification | — | Classification confidence | 90% |
| Publication | Draft | Official distribution | Not verified |
| Channel | Identifier | Current version | Versions | Source |
|---|---|---|---|---|
| npm | confluence-http-api-mcp | 0.1.0 | 1 | Repository |
| Package | Version | Published / observed | Inventory | Security scan |
|---|---|---|---|---|
| npmconfluence-http-api-mcp | 0.1.0Current | Sep 5, 2026 | 5 toolsSucceeded · 0 resources · 0 prompts | Evidence restricted |
Independently scan the exact version your agents use, receive alerts when its risk changes, and investigate every finding with retained version evidence.
No public current-version evidence is available yet.
| Tool | Category | Annotations | Risk |
|---|---|---|---|
confluence_get_pageGet a Confluence page by numeric content id. Returns title, space, ancestors and plain-text body.Input schema{
"type": "object",
"properties": {
"pageId": {
"type": "string",
"description": "Content id, e.g. 123456789"
},
"maxBodyChars": {
"type": "number",
"description": "Truncate body text after N chars (default 12000)",
"default": 12000
}
},
"required": [
"pageId"
]
} | — | — | |
confluence_get_page_by_titleGet a page by space key and exact title (first match).Input schema{
"type": "object",
"properties": {
"spaceKey": {
"type": "string",
"description": "Space key, e.g. GAR"
},
"title": {
"type": "string",
"description": "Exact page title"
},
"maxBodyChars": {
"type": "number",
"default": 12000
}
},
"required": [
"spaceKey",
"title"
]
} | — | — | |
confluence_get_page_childrenList child pages under a parent page (table of contents / doc tree).Input schema{
"type": "object",
"properties": {
"pageId": {
"type": "string",
"description": "Parent content id"
},
"limit": {
"type": "number",
"default": 50
}
},
"required": [
"pageId"
]
} | — | — | |
confluence_list_spacesList Confluence spaces accessible with the token.Input schema{
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "Max spaces (default 50)",
"default": 50
},
"start": {
"type": "number",
"description": "Pagination offset (default 0)",
"default": 0
}
}
} | — | — | |
confluence_searchSearch Confluence pages with CQL. Examples: `space=GAR AND type=page`, `space=GAR AND title ~ "API"`, `text ~ "address search" AND space=GAR`. Returns titles, ids, excerpts.Input schema{
"type": "object",
"properties": {
"cql": {
"type": "string",
"description": "Confluence Query Language expression"
},
"limit": {
"type": "number",
"description": "Max results (default 25, max 50)",
"default": 25
}
},
"required": [
"cql"
]
} | — | — |
| Endpoint | Transport | Authentication | Health | Observed |
|---|---|---|---|---|
| No verified remote endpoint is linked. | ||||
Install the selected package version with: npm install --save-exact confluence-http-api-mcp@0.1.0
confluence-http-api-mcp Server exposed 5 tools during independent protocol observation, including confluence_get_page, confluence_get_page_by_title, confluence_get_page_children, confluence_list_spaces, confluence_search.
The selected current version does not yet have completed public verification. Unknown does not mean clean or vulnerable.
These internal links are derived from strong identity fields such as the implementation name, package, repository, vendor, and listing name—not generic description prose.
Association is based on retained identity fields; it does not by itself prove first-party publication.
Curated product and capability guides containing this catalog record.