{"id":48445696,"url":"https://github.com/neuwcodebox/confluence-mcp","last_synced_at":"2026-04-06T17:31:10.141Z","repository":{"id":345463319,"uuid":"1185810485","full_name":"neuwcodebox/confluence-mcp","owner":"neuwcodebox","description":"An MCP server that helps AI agents navigate Confluence like a human: discover, search, follow hierarchy, and read pages safely within context limits.","archived":false,"fork":false,"pushed_at":"2026-03-19T12:00:42.000Z","size":57,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-19T23:09:55.563Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/neuwcodebox.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-19T00:58:11.000Z","updated_at":"2026-03-19T12:02:36.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/neuwcodebox/confluence-mcp","commit_stats":null,"previous_names":["neuwcodebox/confluence-mcp"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/neuwcodebox/confluence-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuwcodebox%2Fconfluence-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuwcodebox%2Fconfluence-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuwcodebox%2Fconfluence-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuwcodebox%2Fconfluence-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/neuwcodebox","download_url":"https://codeload.github.com/neuwcodebox/confluence-mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuwcodebox%2Fconfluence-mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31483281,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-06T17:22:55.647Z","status":"ssl_error","status_checked_at":"2026-04-06T17:22:54.741Z","response_time":112,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-04-06T17:31:10.053Z","updated_at":"2026-04-06T17:31:10.130Z","avatar_url":"https://github.com/neuwcodebox.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# confluence-mcp\n\nAn MCP server that helps AI agents navigate Confluence like a human: discover, search, follow hierarchy, and read pages safely within context limits.\n\n## Quick start\n\n```bash\nuv sync\nuv run confluence-mcp\n```\n\n## Environment variables\n\nThe server auto-loads a local `.env` file on startup (via `python-dotenv`) for development convenience.\n\n- `CONFLUENCE_BASE_URL` (required): e.g. `https://your-domain.atlassian.net/wiki`\n- `MCP_AUTH_KEY` (optional): server access key. If set, incoming `Authorization` header must match this value.\n- `CONFLUENCE_TOKEN` (optional): default Confluence API token. `X-Confluence-Token` request header takes precedence.\n- `CONFLUENCE_API_VERSION` (optional): `v2` (default) or `v1` for legacy Confluence instances.\n- `CONFLUENCE_SSL_VERIFY` (optional): TLS cert verification toggle (`true` default, set `false` to disable).\n- `CONFLUENCE_CA_BUNDLE` (optional): path to a custom CA bundle file for TLS verification.\n- `CONFLUENCE_CACHE_DIR` (optional): markdown cache directory (default `./cache`)\n- `MAX_MARKDOWN_CHARS` (optional): max markdown body size after conversion (default `12000`)\n- `IN_MEMORY_CACHE_TTL_SECONDS` (optional): API response cache TTL in seconds (default `1800`)\n- `IN_MEMORY_CACHE_SIZE` (optional): API response cache size (default `1000`)\n- `MCP_TRANSPORT` (optional): `stdio` or `streamable-http` (Docker default: `streamable-http`)\n- `MCP_HOST` (optional): host for HTTP mode (`127.0.0.1`, Docker default `0.0.0.0`)\n- `MCP_PORT` (optional): port for HTTP mode (`8000`)\n\n### .env support\n\nExample `.env`:\n\n```dotenv\nCONFLUENCE_BASE_URL=https://your-domain.atlassian.net/wiki\nMCP_AUTH_KEY=your-mcp-auth-key\nCONFLUENCE_TOKEN=your-default-confluence-token\nCONFLUENCE_API_VERSION=v2\nMCP_TRANSPORT=streamable-http\nMCP_HOST=0.0.0.0\nMCP_PORT=8000\n# if needed for self-signed/private CA environments\nCONFLUENCE_SSL_VERIFY=false\n# or: CONFLUENCE_CA_BUNDLE=/path/to/ca-bundle.pem\n```\n\n## Tooling\n\nAll tools return both structured JSON (`structuredContent`) and human-readable markdown text (`content`).\n\n- `search_space_cql`: searches pages with full CQL (including your `space = ...` condition) and returns absolute page URLs.\n- `list_page_children`: returns direct children of a page and always includes parent title.\n- `read_page`: returns markdown content (+TOC), cache metadata, truncation metadata, and optional section-focused view. `header_path` supports array-based hierarchical syntax (e.g., `[\"Top\", \"Child\", \"Target\"]`). If a single name is duplicated, all matched sections are returned. For quick skim, set `header_path=[\"TOC\"]`.\n- `get_page_ancestors`: returns page breadcrumb lineage.\n\n\n### search_space_cql quick examples\n\nThese go into the `cql` argument (the tool automatically adds `space = \u003cspace_key\u003e`):\n\n- `type = \"page\"`\n- `title ~ \"release\"`\n- `text ~ \"runbook\"`\n- `lastmodified \u003e= \"2024/01/01\" ORDER BY lastmodified DESC`\n- `creator = currentUser()`\n- `label NOT IN (archived,obsolete)`\n- `(type = \"page\" AND title ~ \"api\") OR (type = \"blogpost\" AND creator = currentUser())`\n\n## Caching and content shaping\n\n- Uses in-memory LRU+TTL cache for Confluence API responses (default: 1000 entries, 1800s TTL).\n- Reads page version first, then uses cache key `page_id + version`.\n- Cache hit: returns cached markdown immediately.\n- Cache miss: fetches page body, converts HTML to markdown, stores to disk cache.\n- Adds a generated TOC at the beginning of output.\n- Supports section-focused reading via `header_path` option.\n- If content exceeds limit, truncates and appends `...(truncated)`.\n\n## Docker\n\n```bash\ndocker build -t confluence-mcp .\ndocker run --rm -p 8000:8000 \\\n  -e CONFLUENCE_BASE_URL=\"https://your-domain.atlassian.net/wiki\" \\\n  -e MCP_AUTH_KEY=\"your-mcp-auth-key\" \\\n  -e CONFLUENCE_TOKEN=\"your-default-confluence-token\" \\\n  -e MCP_TRANSPORT=\"streamable-http\" \\\n  -e MCP_HOST=\"0.0.0.0\" \\\n  -e MCP_PORT=\"8000\" \\\n  -v confluence-mcp-cache:/data/cache \\\n  confluence-mcp\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneuwcodebox%2Fconfluence-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fneuwcodebox%2Fconfluence-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneuwcodebox%2Fconfluence-mcp/lists"}