mcp-bing-webmaster
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-bing-webmaster Show my top Bing search queries for example.com over the last 28 days."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@mgcrea/mcp-bing-webmaster
A Model Context Protocol server for Bing Webmaster Tools. It lets an agent read a site's Bing search performance, crawl and index state, sitemaps, inbound links and keyword research, and, when you allow it, submit URLs and sitemaps.
The server is read-only by default. Submitting URLs and every other mutating tool are not merely refused when writes are off: they are never registered, so an agent cannot call them at all.
Features
Date windows the API doesn't have. Bing's
Get*Statsmethods take no date range. Each one returns the site's whole history, one row per key per weekly or daily bucket. The server filters that history to your window (the last 28 days by default) and aggregates it per query or page. Clicks and impressions are summed, and positions are averaged weighted by volume. It then sorts and limits the rows, so you get "top 50 queries, last 28 days" rather than the raw table.Clean output. The
{"d": …}envelope is unwrapped and__typetags are dropped./Date(1316156400000-0700)/becomes2011-09-16for a day bucket, or a full ISO timestamp that keeps its offset. The escape hatch gets the same treatment.The site is always explicit. One API key reaches every site its user verified. Every tool therefore takes
siteand resolves it against the sites the key can see.example.com,https://www.example.com/andsc-domain:example.comall work. The tool sends Bing the exact registered form and stamps it on the response. An unknown or ambiguous site is refused with the list of sites the key reaches, so a key from the wrong account shows up immediately instead of answering for another tenant.The key stays secret. Bing puts the API key in the URL. The server never logs, returns or embeds a request URL in an error, and it masks the key in any upstream text that echoes it.
Safe submissions.
bing_webmaster_submit_urlschecks every URL before sending any: it must be on the site's host or, for a site registered at a host root, one of its subdomains (Bing filesblog.example.comunderhttps://example.com/), on its port, under its path, and carry no credentials. URLs are then normalized and deduplicated. The tool usesSubmitUrlorSubmitUrlBatchas appropriate. A POST is never retried automatically, not even after a throttle, because a retry could race the model's own retry and spend quota twice. When it times out or gets a 5xx, the error says the call may have been applied and which tool to check before resubmitting.Bounded calls. Every API call finishes within 45 s, retries included, so the answer arrives before an MCP client gives up. A
Retry-Afterup to 30 s is honoured on GETs. A longer one fails at once with "retry after N s" instead of sleeping inside the tool call. Cancelling a tool call aborts its request to Bing.Remedies, not just errors. Bing's
ErrorCodes (InvalidApiKey,ThrottleUser,NotAuthorized,InvalidUrl,NotAllowed, ...) come back with their name and what to do next.
Related MCP server: mcp-bing-webmaster
Security
Read-only by default.
BING_WEBMASTER_ALLOW_WRITES=1adds the write tools.bing_webmaster_remove_sitemapalso requiresconfirm: true, and so does any non-Getmethod called throughbing_webmaster_request.No runtime dependencies beyond the MCP SDK and Zod. It uses native
fetchthroughout.Your key stays in your environment and is sent only to
ssl.bing.com(or thehttps://proxy you configure).Blast radius. The key can do anything its user can do in Bing Webmaster Tools, on every site that user has. With writes off, the server can only read.
Setup
Sign in at https://www.bing.com/webmasters with a Microsoft, Google or Facebook account.
Add and verify your site. Bing can import sites from Google Search Console, already verified: Add site → Import from GSC.
Open Settings (the gear, top right), then API Access. Accept the terms, then choose API Key → Generate.
Set
BING_WEBMASTER_API_KEYand start the server.bing_webmaster_auth_statuslists the sites the key reaches.
There is one key per user, and it covers all of that user's sites. Deleting or regenerating it breaks every app that uses it, so reuse the existing key.
Configure
Configuration comes from the environment only. The server persists nothing, so there is no config file.
Variable | Required | Description |
| yes | The user's API key (Settings → API Access). |
| no |
|
| no | Base URL override (a proxy). Must be |
| no | GET retry budget (throttling, 5xx, timeouts). 0-10, default 3. POSTs never. |
| no | Per-attempt timeout, 1000-300000, default 30000. Each call ends within 45 s. |
| no |
|
A bad value never stops the server. An out-of-range number is clamped, an unreadable one
falls back to the default, and a non-https API URL falls back to Bing's own endpoint. Each
case is printed at startup and listed under config_warnings in
bing_webmaster_auth_status.
cp .env.example .envQuotas
URL submission is limited per site, per day and per month, and Bing sets the limit by the site's age and standing.
bing_webmaster_get_url_submission_quotashows what is left.SubmitUrlBatchaccepts at most 500 URLs per call, and no more than the remaining quota.Reads have no published quota. Bing throttles a key or site that calls too fast (
ThrottleUser,ThrottleHost), and the server backs off and retries. Since eachGet*Statscall returns the full history, asking for another window costs one call, not a page per day.
Tools
Tool | What it does | Writes |
| Configured? Key accepted? Which sites it reaches (count and list), setup | no |
| The key's sites in registered form, verified or not | no |
| Clicks and impressions over a window: totals and a daily or weekly series | no |
| Top queries over a window: clicks, impressions, CTR, weighted position | no |
| Top pages over a window, same metrics | no |
| For one query, which pages ranked and how | no |
| For one page, which queries it ranked for | no |
| URL inspection: HTTP status, discovered, last crawled, size, anchors | no |
| A live Bingbot fetch's result (status, headers, HTML preview), or the list | no |
| Crawl totals over a window; pages in index and inbound links first → last | no |
| URLs with crawl problems, counted by issue type, most-linked first | no |
| Submitted sitemaps and feeds with status and URL counts | no |
| One sitemap; for an index, its child sitemaps | no |
| The site's pages with inbound links, and how many (paged) | no |
| Who links to one page, with anchor text (paged) | no |
| Keyword research: weekly Bing search volume for a keyword in a market | no |
| Keyword research: related keywords and their volume over a window | no |
| URLs the site may still submit today and this month | no |
| Any API method by name: | gated |
| Submit 1-500 of the site's URLs for crawling (spends quota) | yes |
| Submit a sitemap or feed | yes |
| Remove a sitemap; requires | yes |
| Ask Bingbot to fetch a page now (read the result with | yes |
Some methods have no tool on purpose and are reachable through bing_webmaster_request:
blocked URLs, site roles, crawl settings, site moves, query parameters, deep links,
AddSite/VerifySite/RemoveSite, SubmitContent, GetKeyword, GetUrlTrafficInfo and
GetChildrenUrlInfo.
Things worth knowing
Buckets are kept whole. A weekly bucket counts when its date falls inside the window, even if its week straddles an edge. Every windowed answer reports
buckets(the first and last bucket dates kept, and how many) so "28 days" never quietly means four whole weeks.The newest days are usually empty. Bing's search data lags a few days, and query and page stats are updated weekly. When a window has no rows, the answer gives Bing's actual data range rather than reporting zero traffic.
Top queries and pages only. Totals from
get_query_statsandget_page_statsare smaller than the site's.get_traffic_summaryhas the site totals.Traffic includes every vertical. Since 2023-03-24, Bing counts web, Copilot/chat, news, images, videos and the knowledge panel together.
Keyword research is Bing-wide, not your site's traffic.
impressionscounts searches for exactly the keyword;broad_impressionsadds close variants. A low-volume keyword returns no rows.sitemust already be in Bing Webmaster Tools. Data calls on an unverified site fail withNotAuthorized.bing_webmaster_list_sitesshows the verification codes.Known gap: the AI Performance report (Copilot citations, preview since Feb 2026) has no API. It is only available as a CSV export from the dashboard.
IndexNow is deliberately not part of this server. Wire it into your deploy instead.
Verify live
Checked against the real API on 2026-11-18 (one site, read tools only):
The
{"d": …}envelope and/Date(ms-0700)/dates parse on every read method.GetRankAndTrafficStatsandGetCrawlStatscome back daily.GetQueryStats,GetPageStats,GetQueryPageStatsandGetPageQueryStatscome back weekly, so a 28-day window held two buckets, asbucketsreports.Page rows carry the page URL, and unquoted string parameters (
?page=https://…) work.GetKeywordStatsandGetRelatedKeywords(withYYYY-MM-DDdates) return data. A low-volume keyword returns nothing rather than zeros.Subdomains belong to the root site.
https://mgcrea.io/reports traffic, URL info and sitemaps forcontour.mgcrea.io, so submissions accept a root site's subdomains.GetUrlInfoanswersHttpStatus: 0for crawled pages, sohttp_statusis omitted then.UnknownError(HTTP 400) is transient: the same call succeeded straight after, so GETs retry it.An unknown site fails with the list of sites the key reaches.
SubmitUrlworks, andDailyQuota/MonthlyQuotaare what is left: one submission took them from 100 / 1,300 to 99 / 1,299.
Still unverified:
The other write methods (
SubmitUrlBatch,SubmitFeed,RemoveFeed,FetchUrl).Which error code a spent URL quota returns (assumed
NotAllowed).The
Issuesflags inGetCrawlIssues(the test site had none), positions of 0 or -1, and/Date(-62135596800000)/meaning "no date".
node ../.studio/mcp-template/skill/scripts/live_call.mjs --server . --env-file .env --list \
'[["bing_webmaster_auth_status"], ["bing_webmaster_get_query_stats", {"site": "example.com", "limit": 5}]]'Quick start
pnpm install
pnpm buildThen copy .mcp.json.example to .mcp.json and fill it in.
Inspect the tools
printf '%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"cli","version":"0"}}}' \
'{"jsonrpc":"2.0","method":"notifications/initialized"}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/list"}' \
| node dist/cli.js 2>/dev/null | jq -r '.result.tools[]?.name'Develop
pnpm dev # tsdown --watch
pnpm test # vitest
pnpm typecheck
pnpm lint
pnpm formatPublish
pnpm dlx release-it # bump, commit, tag
git push --follow-tags # CI publishes to npm + GHCR from the tagLicense
MIT
Available Tools
19 toolsbing_webmaster_auth_statusBing Webmaster: Auth StatusARead-only
Whether an API key is configured and accepted, and which sites it reaches (count and list, with verification state). The key belongs to a user, not a site, and reaches every site that user verified — this is how to see which account it is. When unconfigured, returns the exact steps to create a key. Call this first when a tool you expected is missing. Costs one GetUserSites call (cached for 5 minutes).
Inputs: no named parameters.
bing_webmaster_get_crawl_issuesBing Webmaster: Get Crawl IssuesARead-only
The site's URLs with crawl problems, counted by issue type (Code4xx, Code5xx, Code301, Code302, BlockedByRobotsTxt, ImportantUrlBlockedByRobotsTxt, ContainsMalware, DnsErrors, TimeOutErrors), then the URLs themselves, most-linked first, capped by limit. A fixed issue can take a few days to drop off Bing's list.
Inputs: site (required), issue, limit.
bing_webmaster_get_crawl_statsBing Webmaster: Get Crawl StatsARead-only
How Bingbot crawled the site over a date window: pages crawled, crawl errors, responses by status class (2xx, 301, 302, 4xx, 5xx), robots.txt blocks, malware, DNS failures and timeouts, summed over the window; plus pages in the index and inbound links as first/last values (those are levels, not counters). Bing keeps about six months of daily rows and returns them all in one call; this tool filters them.
Inputs: site (required), end_date, start_date, include_series.
bing_webmaster_get_fetched_urlBing Webmaster: Get Fetched URLARead-only
The result of a live Bingbot fetch (requested with bing_webmaster_fetch_url, or from the dashboard's URL Inspection): status, response headers and the HTML Bingbot received. Without url, lists the URLs fetched so far. A fetch takes a minute or two to complete after it is requested.
Inputs: site (required), url, limit, max_document_chars.
bing_webmaster_get_keyword_statsBing Webmaster: Get Keyword StatsARead-only
Keyword research: how often a keyword was searched on Bing, as a weekly series (about six months of history) with totals over the window. This is Bing-wide search demand, not your site's traffic, so it takes no site. Impressions count searches for exactly this keyword (strict match); broad_impressions add close variants. A keyword with too little volume in the market returns no rows rather than zeros. For ideas around a keyword, use bing_webmaster_get_related_keywords.
Inputs: query (required), country, end_date, language, +1 more.
bing_webmaster_get_link_countsBing Webmaster: Get Link CountsARead-only
The site's pages that have inbound links from other sites, with how many each has, one page of results at a time (page 0 first; the answer gives total_pages and next_page). For who links to one page, and with what anchor text, use bing_webmaster_get_url_links.
Inputs: site (required), page.
bing_webmaster_get_page_queriesBing Webmaster: Get Page QueriesARead-only
For one page of the site, the search queries it appeared for on Bing and how each performed (clicks, impressions, CTR, position) over a date window. Bing has no date parameter on this method: one call returns the site's whole history, which this tool filters to the window, aggregates per key, sorts and cuts. Calling it again with another window costs the same single call.
Inputs: page (required), site (required), limit, sort_by, +3 more.
bing_webmaster_get_page_statsBing Webmaster: Get Page StatsARead-only
The site's pages that appeared in Bing search over a date window, each with clicks, impressions, CTR and average position. Bing only reports its top pages. For the queries behind one page, use bing_webmaster_get_page_queries. Bing updates this weekly. Bing has no date parameter on this method: one call returns the site's whole history, which this tool filters to the window, aggregates per key, sorts and cuts. Calling it again with another window costs the same single call.
Inputs: site (required), limit, sort_by, contains, +2 more.
bing_webmaster_get_query_pagesBing Webmaster: Get Query PagesARead-only
For one search query, which of the site's pages Bing showed and how each performed (clicks, impressions, CTR, position) over a date window. Use it to find the page that ranks for a query, or two pages competing for it. Bing has no date parameter on this method: one call returns the site's whole history, which this tool filters to the window, aggregates per key, sorts and cuts. Calling it again with another window costs the same single call.
Inputs: site (required), query (required), limit, sort_by, +2 more.
bing_webmaster_get_query_statsBing Webmaster: Get Query StatsARead-only
The search queries the site appeared for on Bing over a date window, each with clicks, impressions, CTR and average position (impression-weighted across Bing's buckets; click_position is weighted by clicks). Bing only reports its top queries, so totals here are less than the site's — use bing_webmaster_get_traffic_summary for site totals. Bing updates this weekly. Bing has no date parameter on this method: one call returns the site's whole history, which this tool filters to the window, aggregates per key, sorts and cuts. Calling it again with another window costs the same single call.
Inputs: site (required), limit, sort_by, contains, +2 more.
bing_webmaster_get_sitemapBing Webmaster: Get SitemapARead-only
Details of one submitted sitemap. For a sitemap index, lists the child sitemaps it points to, each with status, URL count and last crawl.
Inputs: site (required), sitemap_url (required), limit.
bing_webmaster_get_traffic_summaryBing Webmaster: Get Traffic SummaryARead-only
The site's Bing search clicks and impressions over a date window: totals plus a series, as Bing reports it (daily) or rolled up by week. Since 2023-03-24 Bing counts every vertical here — web, Copilot/chat, news, images, videos. Start here for 'how is the site doing on Bing'; then bing_webmaster_get_query_stats or bing_webmaster_get_page_stats for the breakdown. Bing has no date parameter on this method: one call returns the site's whole history, which this tool filters to the window, aggregates per key, sorts and cuts. Calling it again with another window costs the same single call.
Inputs: site (required), end_date, interval, start_date.
bing_webmaster_get_url_infoBing Webmaster: Get URL InfoARead-only
Bing's URL inspection for one page: whether Bing knows it, the HTTP status it last got, when it was discovered and last crawled, document size, anchor count, and how many URLs Bing knows below it. Prefer this over a site: web search to check whether Bing has a page — a search result is neither complete nor current. url may also be "domain:example.com" for the whole domain.
Inputs: url (required), site (required).
bing_webmaster_get_url_linksBing Webmaster: Get URL LinksARead-only
The external pages linking to one page of the site, with their anchor text, one page of results at a time (page 0 first; the answer gives total_pages and next_page).
Inputs: url (required), site (required), page.
bing_webmaster_get_url_submission_quotaBing Webmaster: Get URL Submission QuotaARead-only
How many URLs the site may still submit through bing_webmaster_submit_urls: today (daily_quota) and this month (monthly_quota). The quota is per site and Bing sets it by the site's age and standing, so it differs between sites. Check it before a large submission: Bing caps a batch at what is left, so a bigger one fails.
Inputs: site (required).
bing_webmaster_list_sitemapsBing Webmaster: List SitemapsARead-only
The sitemaps and feeds submitted for the site (top level only), each with its type, processing status, URL count, size and when Bing last crawled it. For the children of a sitemap index, use bing_webmaster_get_sitemap.
Inputs: site (required), limit.
bing_webmaster_list_sitesBing Webmaster: List SitesARead-only
Every site the API key's user has added to Bing Webmaster Tools, in its registered form (scheme and trailing slash as Bing stores them), with whether it is verified. Unverified sites carry their verification codes. Every other tool takes one of these as site; data calls on an unverified site fail with NotAuthorized.
Inputs: limit.
bing_webmaster_requestBing Webmaster: RequestARead-only
Escape hatch: call any Bing Webmaster API method that has no dedicated tool, by name — e.g. GetBlockedUrls, GetCrawlSettings, GetQueryParameters, GetSiteRoles, GetSiteMoves, GetUrlTrafficInfo, GetChildrenUrlInfo, GetKeyword, GetQueryPageDetailStats. Methods: https://learn.microsoft.com/en-us/dotnet/api/microsoft.bing.webmaster.api.interfaces.iwebmasterapi. Get* methods are GET with params in params; everything else is POST with a JSON body. A siteUrl in params or body is resolved to its registered form first. The answer is normalized (the d envelope unwrapped, __type dropped, dates ISO) but not shaped, and cut at max_chars — prefer the dedicated tools. Writes are DISABLED: only Get* methods are allowed. Set BING_WEBMASTER_ALLOW_WRITES=1 to allow others.
Inputs: method_name (required), body, http, params, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 19 tools
Each tool targets a distinct resource and the descriptions explicitly route between similar ones (traffic_summary vs query_stats vs page_stats, query_pages vs page_queries). The inverse pair bing_webmaster_get_query_pages / bing_webmaster_get_page_queries is the one spot where a careless agent could swap them, but the docs distinguish them clearly.
All tools carry the bing_webmaster_ prefix with a predictable verb_noun form (get_*, list_*, plus a few object-named reads). Minor deviations like auth_status and the generic request tool don't break the pattern.
19 tools is on the heavy side but justified: read-only analytics, crawl, sitemap, link and keyword domains each need several endpoints. Almost every tool earns its place, with the generic request acting as a documented overflow valve rather than filler.
Read coverage is broad, but the surface has dead ends: get_url_submission_quota references bing_webmaster_submit_urls and get_fetched_url references bing_webmaster_fetch_url, neither of which exists as a tool, and writes are globally disabled. Agents can therefore see quota but never submit URLs, and cannot trigger a fetch despite being told how to read one.
Maintenance
Related MCP Connectors
Read-only Search Console analytics, URL inspection, indexing diagnostics, and sitemaps.
Read-only Google Search Console, Bing, Google Analytics and privacy-friendly analytics for your AI.
Google Search Console for AI assistants: traffic, rankings, indexing and page checks. Read-only.
Read-only Google Search Console and Google Analytics for AI agents.
Related MCP Servers
- AlicenseBqualityCmaintenanceProvides AI agents full access to Bing Webmaster Tools API for site management, URL submission, sitemaps, traffic stats, keyword research, and URL blocking.248 npm1MIT
- AlicenseBqualityDmaintenanceProvides secure, read-only access to Bing Webmaster Tools analytics and non-destructive URL submission for indexing, without destructive site management capabilities.16MIT
- AlicenseAqualityBmaintenanceBing Webmaster Tools and IndexNow for AI agents: traffic, indexing, crawl issues, inbound links, keywords. Direct writes are off by default; changes go through a plan a person applies.631MIT
- AlicenseCqualityBmaintenanceEnables AI assistants to query Bing Webmaster Tools data such as site verification, traffic analytics, and search performance, with read-only defaults and configurable site access controls.34MIT