Dock0

Connect Claude, Cursor, VS Code and other AI tools to Exa's search, code search, and research capabilities via MCP.

Checked 4/12/2026, 3:26:17 PM

Last called Never

Last deployed Never

0 stars

Connect

Use this MCP endpoint

Create a key, paste the endpoint into your MCP client, then run a quick probe to confirm the connection works end-to-end.

https://dock0.mcp.dock0.dev/exa/mcphttps://dock0.mcp.dock0.dev/exa/mcp

tools/list probe

curl -sS \
  -H 'Authorization: Bearer <YOUR_MCP_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":"1","method":"tools/list","params":{}}' \
  https://dock0.mcp.dock0.dev/exa/mcp

Before you start

Pricing and call-balance policy

This server is currently free to use.

You can still create a key and connect it the same way as any paid server.

Step 1: sign in. Step 2: create a key. Step 3: paste the generated client config into Claude, Cursor, or Claude Code.

Sign in to create a key

Dock0 generates a buyer-scoped key and a ready-to-paste client guide after sign-in.

pricing

Free

Free to use

total calls

Lifetime traffic

success rate

100.0%

0 non-success calls

p95 latency

0ms

Lifetime p95

stars

Community saves

Capabilities

2 tools • 1 prompts • 1 resources

Refreshed 4/12/2026, 3:26:17 PM

Tools (2)

web_search_exa

Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results, ready for LLM use. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people to specifically search through Linkedin profiles and category:company to search through company pages. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.

Input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Natural language search query. Should be a semantically rich description of the ideal page, not just keywords. Optionally include category:<type> (company, people) to focus results — e.g. 'category:people John Doe software engineer'."
    },
    "numResults": {
      "type": "number",
      "maximum": 100,
      "minimum": 1,
      "description": "Number of search results to return (must be a number, default: 10)."
    }
  },
  "additionalProperties": false
}

web_fetch_exa

Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).

Input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "urls"
  ],
  "properties": {
    "urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "URLs to read. Batch multiple URLs in one call."
    },
    "maxCharacters": {
      "type": "number",
      "minimum": 1,
      "description": "Maximum characters to extract per page (must be a positive number, default: 3000)"
    }
  },
  "additionalProperties": false
}