Read and write knowledge-base articles, categories, snippets, glossary, readers, and search data. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"knowledgeowl": {
"url": "https://knowledgeowl.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"knowledgeowl": {
"type": "http",
"url": "https://knowledgeowl.usefulapi.io/mcp"
}
}
}Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your KnowledgeOwl API key.
Find it in KnowledgeOwl → Account → API keys. Your key is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your KnowledgeOwl API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the KnowledgeOwl connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
list_articles | read | List articles List knowledge-base articles. KnowledgeOwl API: GET /article.json. Optionally filter by project_id (the knowledge base). Returns the list envelope { valid, page_stats, data:[...] }. |
get_article | read | Get an article Fetch a single article by id. KnowledgeOwl API: GET /article/{id}.json. Returns { valid, data:{...} }. |
list_categories | read | List categories List categories (the article tree/table of contents). KnowledgeOwl API: GET /category.json. Optionally filter by project_id. Returns { valid, page_stats, data:[...] }. |
get_category | read | Get a category Fetch a single category by id. KnowledgeOwl API: GET /category/{id}.json. |
list_tags | read | List tags List article tags. KnowledgeOwl API: GET /tag.json. Returns { valid, page_stats, data:[...] }. |
list_snippets | read | List snippets List reusable content snippets. KnowledgeOwl API: GET /snippet.json. Returns { valid, page_stats, data:[...] }. |
list_glossary_terms | read | List glossary terms List glossary terms and definitions. KnowledgeOwl API: GET /glossaryterm.json. Returns { valid, page_stats, data:[...] }. |
list_comments | read | List comments List reader comments / feedback on articles. KnowledgeOwl API: GET /comment.json. Returns { valid, page_stats, data:[...] }. |
list_readers | read | List readers List readers (knowledge-base end users / audience accounts). KnowledgeOwl API: GET /reader.json. Returns { valid, page_stats, data:[...] }. |
get_reader | read | Get a reader Fetch a single reader by id. KnowledgeOwl API: GET /reader/{id}.json. |
list_files | read | List files List files in the file library (images/attachments). KnowledgeOwl API: GET /file.json. Returns { valid, page_stats, data:[...] }. |
list_article_versions | read | List article versions List article versions. KnowledgeOwl API: GET /articleversion.json. Returns { valid, page_stats, data:[...] }. |
list_article_revisions | read | List article revisions List article revision history (read-only audit trail). KnowledgeOwl API: GET /articlerevision.json. Returns { valid, page_stats, data:[...] }. |
list_suggestions | read | List search suggestions List search suggestions / reader search analytics (what readers searched for). KnowledgeOwl API: GET /suggest.json. Returns { valid, page_stats, data:[...] }. |
list_synonyms | read | List synonyms List search synonyms (terms treated as equivalent by search). KnowledgeOwl API: GET /synonym.json. Returns { valid, page_stats, data:[...] }. |
list_webhooks | read | List webhooks List configured webhooks. KnowledgeOwl API: GET /webhook.json. Returns { valid, page_stats, data:[...] }. |
list_authors | read | List authors List authors/agents (the team members who write and manage content). KnowledgeOwl API: GET /agent.json. Returns { valid, page_stats, data:[...] }. |
knowledgeowl_request | read | Raw read request Power-user escape hatch: GET any KnowledgeOwl API path not wrapped by a dedicated tool. READ-ONLY — only GET is allowed. Pass the FULL API path after the base, starting with a slash, INCLUDING any query string, e.g. "/article.json?_page=2" or "/category/abc123.json". Returns the parsed JSON. |
create_article | write | Create an article MUTATES KnowledgeOwl data: creates a new article. KnowledgeOwl API: POST /article.json (JSON). Required by the API: project_id, name, status, url_hash, visibility, and current_version (a nested object `{ <lang>: { title, body, ... } }` — pass it via the `fields` passthrough). Returns the created article. |
update_article | write | Update an article MUTATES KnowledgeOwl data: updates an existing article. KnowledgeOwl API: PUT /article/{id}.json (JSON — only included fields change). Use the `fields` passthrough for current_version (title/body) and any other documented field. The path id is never sent in the body. |
create_category | write | Create a category MUTATES KnowledgeOwl data: creates a new category (a node in the article tree). KnowledgeOwl API: POST /category.json (JSON). Required by the API: type, project_id, url_hash, name, visibility, status. Pass extra documented fields via `fields`. Returns the created category. |
update_category | write | Update a category MUTATES KnowledgeOwl data: updates an existing category. KnowledgeOwl API: PUT /category/{id}.json (JSON — only included fields change). Use the `fields` passthrough for any other documented field. The path id is never sent in the body. |
create_snippet | write | Create a snippet MUTATES KnowledgeOwl data: creates a reusable content snippet. KnowledgeOwl API: POST /snippet.json (JSON). Pass the snippet body/content and any other documented field via `fields` (e.g. snippet_text/body). Returns the created snippet. |
create_glossary_term | write | Create a glossary term MUTATES KnowledgeOwl data: creates a glossary term and definition. KnowledgeOwl API: POST /glossaryterm.json (JSON). Pass extra documented fields via `fields`. Returns the created glossary term. |
knowledgeowl_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
knowledgeowl_request_feature | Request a missing feature Tell usefulapi that the user needs something the KnowledgeOwl tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
knowledgeowl_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED KnowledgeOwl tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
knowledgeowl_cancel_subscription | Cancel the Pro subscription Cancel the caller's KnowledgeOwl Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run knowledgeowl_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited |
Pro covers this KnowledgeOwl server only. Subscribe with knowledgeowl_upgrade (it returns a Stripe Checkout link). Cancel any time with knowledgeowl_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running knowledgeowl_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by KnowledgeOwl. The server calls the KnowledgeOwl API with your own KnowledgeOwl access, so it sees only the data that your account can see.
The login page asks for your KnowledgeOwl API key. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your KnowledgeOwl API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the KnowledgeOwl API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in KnowledgeOwl.
Yes, if you approve it. 6 of the 24 KnowledgeOwl tools can create or change data. The other 18 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this KnowledgeOwl server only. Run knowledgeowl_usage_status to see how many calls you used.
Ask the AI to run knowledgeowl_upgrade: it returns a Stripe Checkout link. To cancel, run knowledgeowl_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with knowledgeowl_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.