Bing Copilot MCP server

Registry name: io.github.johnisanerd/bing-copilot. Maintained by AlphaOSINT (Apify developer johnvc, GitHub johnisanerd).

What it does

Get the Copilot AI answer Bing shows for a query, with the answer text in structured blocks, the sources it cites and the brands it mentions.

The Microsoft side of AI answer tracking, alongside Google AI Overview. Use it for answer-engine optimization, brand monitoring and checking which sources Copilot cites.

This server is not self-hosted. It runs on Apify’s hosted MCP endpoint (mcp.apify.com), which starts the Apify Actor johnvc/bing-copilot-api for each tool call. You need an Apify account, and every call is billed to that account at the Actor’s prices below. Apify’s own pricing and terms apply to the account.

Charge Price (USD) What it covers
Copilot query resolved $0.015 One AI answer resolution: the answer, its structured text blocks, and its cited references when present.

Prices shown are Apify’s free-plan rates; paid Apify plans get lower per-event prices. Prices change from time to time; the Actor’s page on Apify shows the current ones.

Data source and terms

Microsoft’s public Copilot answers in Bing search, collected by scraping. The server returns the data as published at the time of the call. You are responsible for using it in line with the source’s terms and the laws that apply to you. AlphaOSINT is not affiliated with the source.

Endpoint

Setup

Claude Code

claude mcp add --transport http bing-copilot "https://mcp.apify.com/?tools=johnvc/bing-copilot-api"

VS Code (.vscode/mcp.json)

{
  "servers": {
    "bing-copilot": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=johnvc/bing-copilot-api"
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "bing-copilot": {
      "url": "https://mcp.apify.com/?tools=johnvc/bing-copilot-api"
    }
  }
}

Claude Desktop (Settings → Connectors → Add custom connector, paste the URL). Older versions without remote connectors can bridge through mcp-remote in claude_desktop_config.json:

{
  "mcpServers": {
    "bing-copilot": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.apify.com/?tools=johnvc/bing-copilot-api"
      ]
    }
  }
}

Each client opens an Apify sign-in (OAuth) on first use. To use a token instead, send Authorization: Bearer <APIFY_TOKEN> as a header; create one under Apify Console → Settings → API & Integrations.

Tools

Tool What it does
johnvc--bing-copilot-api Runs the Actor with the parameters below and returns the result rows.
get-actor-run Status of a run started by the tool, for long runs.
get-dataset-items Pages through a run’s full output by datasetId when it is larger than the inline result.
get-key-value-store-record Reads a record a run stored, such as a run report.
abort-actor-run Stops a run.

Apify’s endpoint adds the four helper tools automatically whenever an Actor tool is loaded.

Parameters of johnvc--bing-copilot-api

Parameter Type Required Default Description
query string   "best crm for startups" REQUIRED (or use queries). A question or search phrase to resolve, e.g. ‘best crm for startups’. Anything you would type into the answer engine works.
queries array     Provide a list of queries to resolve in one run, e.g. [‘best crm for startups’, ‘best help desk software’]. Each query returns one AI answer row.
brandToTrack string     Optional brand or product name, e.g. ‘Salesforce’. Each answer row then includes a brandMentioned boolean showing whether the brand appears in the AI answer text or its cited sources.

Example arguments:

{
  "query": "best crm for startups"
}

Output

The tool returns JSON rows with these fields.

Field Type Description
result_type string: copilot_answer, error Discriminator for the row kind. Use it to filter the dataset.
query string The query this AI answer was resolved for.
answerPresent boolean True when the engine returned an AI answer for this query.
answerHeader string The one-paragraph headline answer, when the engine provides one.
markdown string The full AI answer rendered as one markdown document: headings, paragraphs, nested lists, tables, and code blocks.
textBlocks array The structured answer blocks exactly as returned: paragraph, heading, list (possibly nested), code_block, and table entries.
references array The sources the AI answer cites: index, title, link, snippet, and source name.
headerVideo object The featured video shown above the answer, when present: title, link, duration, channel, views.
imagesLink string Link to the image results for the query, when the engine returns one.
videosLink string Link to the video results for the query, when the engine returns one.
brandToTrack string The brand checked for mentions, echoed from the input when provided.
brandMentioned boolean True when the tracked brand appears in the AI answer text or its cited sources. Only present when brandToTrack is set.
summary string One-line human-readable summary of the answer, built for AI agents.
note string Extra context when no answer was returned for the query.
fetched_at string ISO-8601 timestamp of when this row was fetched.
error_message string Human-readable error description on error rows.
error_type string Machine-readable error class on error rows, e.g. MissingRequiredParameter or CopilotError.