RAG Search over your content powered by Inkeep
If you want an AI assistant working directly with Inkeep, the inkeep mcp server is the bridge. RAG Search over your content powered by Inkeep.
Note the full path of the project, referred to as <YOUR_INKEEP_MCP_SERVER_ABSOLUTE_PATH> in a later step.
Once connected, the assistant can call this tool directly:
Dependencies — The Dependencies tool exposed by this serverSetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
Before the server will start you need to supply 7 environment variables: INKEEP_API_BASE_URL, INKEEP_API_KEY, INKEEP_API_MODEL, INKEEP_MCP_TOOL_NAME, INKEEP_MCP_TOOL_DESCRIPTION, YOUR_INKEEP_MCP_SERVER_ABSOLUTE_PATH, YOUR_INKEEP_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.
AI-service servers chain other models into your assistant, turning a single chat into a small production pipeline. Inkeep sits in that group, and the shape of its toolset — Dependencies — tells you what it is really for. Worth comparing against the other ai services servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Dependencies | The Dependencies tool exposed by this server. |
| Variable | Description | Required |
|---|---|---|
| INKEEP_API_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| INKEEP_API_KEY | Credential the server authenticates with. | Yes |
| INKEEP_API_MODEL | Configuration value read at startup. | Optional |
| INKEEP_MCP_TOOL_NAME | Configuration value read at startup. | Optional |
| INKEEP_MCP_TOOL_DESCRIPTION | Configuration value read at startup. | Optional |
| YOUR_INKEEP_MCP_SERVER_ABSOLUTE_PATH | Filesystem location the server is allowed to use. | Optional |
| YOUR_INKEEP_API_KEY | Credential the server authenticates with. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.