Agent view · Findings · 2026-11-14
One in four MCP hosts changed its tools in four days. Nothing told the agent.
This is the response this server returns to a client that asks for Accept: text/markdown at https://crawlcheck.io/blog/one-in-four-mcp-hosts-changed-its-tools-in-four-days: fetched when you opened this page, shown byte for byte. An assistant, a crawler that negotiates markdown, or anything reading our feed gets exactly this. The markdown leaves signed (RFC 9421, key in our key directory), so a crawler can prove the page it read is the page this server sent; the check is shown below.
| status | 200 |
|---|---|
| content-type | text/markdown; charset=utf-8 |
| vary | Accept |
| link | <https://crawlcheck.io/llms.txt>; rel="describedby"; type="text/plain", <https://crawlcheck.io/.well-known/api-catalog>; rel="service-desc"; type="application/linkset+json", <https://crawlcheck.io/blog/one-in-four-mcp-hosts-changed-its-tools-in-four-days>; rel="cite-as", <https://crawlcheck.io/.well-known/http-message-signatures-directory>; rel="http-message-signatures-directory" |
| cache-control | public, max-age=900, stale-while-revalidate=2400 |
| bytes | 12,279 |
| words | 1,746 |
| sha-256 | 66c409933279597f3f145de0f79eb22a10688af148466d959960ededcb489575 |
| repr-digest | sha-256=:ZsQJkzJ5WX8/FF3g956yKhBoivFIRm2VmWDt7ctIlXU=: ← matches the body shown |
| signature-input | sig1=("@authority";req "@path";req "repr-digest" "content-type");created=1795179355;expires=1795182955;keyid="1hHmE3fo1rg5Ig70wuFtJ5wBc7G-sUTgUJkxyPWFRps";alg="ed25519";nonce="MqwWZU1BIw0g3YNxHCnrXQ";tag="crawlcheck-page" |
| signature | sig1=:1+007AvJol/IKCOb/YN/e4svUuMR/q6vub8yiI290gYZ8aNyznAtOnFnO/KsicHWstGXnmAxrjrXOHCWlkZ/Cw==: |
| verified | yes — signature by key 1hHmE3fo1rg5Ig70… from https://crawlcheck.io/.well-known/http-message-signatures-directory (directory valid), valid for 3600 more s. Checked here exactly as a crawler would; redo it yourself: https://crawlcheck.io/api/tool/wba |
Findings · 2026-11-14 · By [VSNARY | Emmanuel Orta](/author) # One in four MCP hosts changed its tools in four days. Nothing told the agent. We re-read the tool list of every public server in the MCP Registry. Most changes rewrote a description, and most kept the same version number. Between 10 and 14 November 2026, 706 of 3,167 hostnames in the MCP Registry (22.3%) served a different tool list than the one CrawlCheck read before. 83.9% of recent changes rewrote a tool description, and 71% of the latest 500 kept the same server version number. An agent approved against the earlier list is now using tools nobody re-reviewed. On this page - What we counted - What changed - The version number did not move - What this does not say - What to do about it The last 440 changes, by kind (a change can fall in more than one row) A tool description was rewritten 369 (83.9%) A tool was added 207 (47%) A tool was removed 36 (8.2%) Only inputs or annotations changed 36 (8.2%) When you connect an [AI agent](/glossary/ai-agent) to an [MCP server](/glossary/mcp-server), you approve a list of tools: their names, their descriptions and what they are allowed to do. That approval is a snapshot. The server can change the list the next day, and nothing in the protocol tells the agent or you. We wanted to know how often that happens, so we counted. Every figure here was read on 14 November 2026. ## What we counted # We re-read every public server in the [MCP](/glossary/mcp) Registry that answers without a login. We ask for the tool list and compare it with the previous read. We never call a tool. - 6,744 servers returned a tool list. 4,953 of those lists (73.4%) were not the list we read before. - That figure counts registry entries, and one publisher can list thousands of near-identical entries on one host. Counted by host, it is 706 of 3,167 (22.3%). By registered domain, 677 of 2,843 (23.8%). - The median gap between the two reads was 8.7 days. So the fair headline is the smaller one: about one host in four changed its tools in four days. ## What changed # The last 440 changes, recorded on 13 and 14 November. A change can fall in more than one row. | Change | Servers | Share | | --- | --- | --- | | A tool description was rewritten | 369 | 83.9% | | A tool was added | 207 | 47% | | A tool was removed | 36 | 8.2% | | Only inputs or annotations changed | 36 | 8.2% | The first row matters most. A tool's description is the text the model reads to decide when to call the tool and how. Rewrite it and the agent can behave differently, while everything the user sees stays the same. ## The version number did not move # We looked at the latest 500 changes, recorded over about 40 hours from 12 to 14 November, across 315 hosts. - **353 of the 499 that report a version (71%)** reported the same server version before and after the change. Checking the version number would have missed them. - **9 of 500** were servers that had declared every tool read-only and then added tools that are not, such as booking or cancelling an appointment. - **16 of 500** widened what an existing tool is declared to do, for example a tool newly declared destructive. ## What this does not say # A changed tool is a reason to review, not evidence of bad intent. Most changes are ordinary releases. None of the 440 changes above matched a known poisoning pattern. We only read servers that answer without a login. Servers read for the first time count in the totals but cannot have changed, so the shares are floors. Packages that run on your own machine are counted apart: of 2,860 that returned a tool list, 136 changed between two reads. ## What to do about it # - **Record what you approved.** Keep the tool names, descriptions and input schemas from the day you reviewed the server, not only its name and version. - **Compare on every connection.** If the list no longer matches the record, stop and look before the agent acts. - **Do not rely on the version number.** Most of the changes we saw kept it. - **Re-review these three first:** a rewritten description, a removed tool, and a read-only server that gains a tool that writes. The full feed of changes is public at [/mcp/changes](/mcp/changes), the live figures are on the [research page](/research/mcp-tool-changes), and every change is published weekly as a [signed dataset](/data/mcp-changes/index.json). *Published by CrawlCheck, which sells a check for the problem described here.* CrawlCheck’s dataset when this page loaded: 570,959 sites measured. Written by [Emmanuel Orta](/author) · VSNARY I build CrawlCheck and write everything published here, from measurements the verification layer took. Where a post got something wrong, the correction stays in the post. [Every post, and where I got it wrong →](/author) · [Follow on LinkedIn →](https://www.linkedin.com/in/emmanuelorta) Share this finding: [LinkedIn](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fcrawlcheck.io%2Fblog%2Fone-in-four-mcp-hosts-changed-its-tools-in-four-days%3Futm_source%3Dlinkedin%26utm_medium%3Dsocial%26utm_campaign%3Dshare)[X](https://twitter.com/intent/tweet?url=https%3A%2F%2Fcrawlcheck.io%2Fblog%2Fone-in-four-mcp-hosts-changed-its-tools-in-four-days%3Futm_source%3Dx%26utm_medium%3Dsocial%26utm_campaign%3Dshare&text=One%20in%20four%20MCP%20hosts%20changed%20its%20tools%20in%20four%20days.%20Nothing%20told%20the%20agent.)[Email](mailto:?subject=One%20in%20four%20MCP%20hosts%20changed%20its%20tools%20in%20four%20days.%20Nothing%20told%20the%20agent.&body=https%3A%2F%2Fcrawlcheck.io%2Fblog%2Fone-in-four-mcp-hosts-changed-its-tools-in-four-days)[Follow Emmanuel on LinkedIn](https://www.linkedin.com/in/emmanuelorta) ## Questions this post answers ### How often do MCP servers change their tools? Between 10 and 14 November 2026, 706 of 3,167 hostnames in the MCP Registry (22.3%) served a different tool list than the one read before. Counted by registry entry it was 4,953 of 6,744. ### Does the server version number show that an MCP server's tools changed? Often not. Of the latest 500 changes recorded from 12 to 14 November 2026, 353 of the 499 that report a version kept the same one. ### What should I do when an MCP server's tool list changes? Compare the list with the one you approved before the agent acts. Review a rewritten description, a removed tool, or a read-only server that gains a tool that writes first. ## Related findings [2026-10-08 How to check an MCP server is safe before an agent connects Handshake, list the tools, read each description as an instruction to a model, check the sign-in reply, pin what you read. Eleven](/guides/how-to-check-an-mcp-server-before-an-agent-connects)[2026-10-15 MCP reliability, October 2026: 39,484 handshakes measured 98.7% of 39,484 handshakes with 6,000 registry MCP servers were answered, 8–15 October 2026, and one endpoint in five changed its](/blog/mcp-reliability-october-2026)[2026-11-13 Both our SDKs cut a tool list at 300 with no warning CrawlCheck's lockfile and both SDKs fingerprinted only the first 300 tools of an MCP server, unmarked. Fixed 11 November 2026.](/blog/our-sdks-cut-a-tool-list-at-300-with-no-warning) The main product Found this on your own site? **We fix it for $100.** Scan free to see where you stand. The fix is one site, every finding implemented and re-measured, with a sealed before and after. [Fix it all — $100](https://buy.stripe.com/4gM00j7OjawhdLEdyR2VG0v) [What it covers](/pricing#fix) · [scan first, it is free](/) Free browser extension Check this on any site you open, **without leaving the page.** CrawlCheck for Chrome grades every site you visit A–F and shows, from your own browser, what search engines and AI assistants are actually served. Free, no account. [Add to Chrome — free](https://chromewebstore.google.com/detail/plgjengobhbdmbgckiiaaflgiepdbcpi?utm_source=crawlcheck.io&utm_medium=post) [What it does](/extension) Write for the library Measured something yourself? **Submit an article.** Send your finding, the data and the method. A person reads every submission and replies by email; accepted articles are published under your name with a link to your study. Free to submit. Articles are accepted on merit; no one can pay to have one published. [Submit an article](/submit-finding#send) [How it works](/submit-finding) · a reply within about a week Spotted a mistake or a bug on this page? [Report an error](/report-error?k=article). Confirmed errors are fixed and logged on the [corrections page](/corrections). ## Comments Comments are read before they appear. Nothing is published automatically, and no account is needed. An AI agent with a published signing key can post without the queue: it signs the request and the signature is checked against its own domain ([how](/api/comment/signed)). Those appear at once, marked *verified*. Send for review Writing about this? [Facts, live figures and marks](/press) — every number on that page is dated and traceable to a scan. [All findings](/blog) · [The dataset](/data) · [How the dataset works](/policy) We read your site the way crawlers do, from our own network, and every report says exactly what was asked for and what came back. [Who runs this](/author) · [Press kit](/press) · [Videos](/videos) · [Evidence for disputes](/evidence) · [YouTube](https://www.youtube.com/@crawlcheck) · [hello@crawlcheck.io](mailto:hello@crawlcheck.io) #### How we measure, and our own machine files CrawlCheck reads every site as itself. Its crawler-identity tests send named user-agent strings from its own network, never from an operator’s published range, so a site that verifies crawlers can tell them apart; every report says so. Results reflect what an anonymous non-browser client receives. [What we collect and how to opt out](/policy) · [how every report is timestamped](/proof) · [who runs this](/author) · [press kit](/press) · [hello@crawlcheck.io](mailto:hello@crawlcheck.io). **Second vantage:** the [browser extension](/extension) measures what crawlers are served from your own address and after your JavaScript runs — the half this server cannot see. From 1.0.0 it sends the domain you ask about, on one button, and anonymous usage counts you can switch off; from 1.0.3 a footer switch turns off the hostname lookup for the grade on the icon; from 1.0.4 a share switch, on by default, sends a signed Two-vantages reading (status, size, words and a hash per identity; never page text); from 1.0.16 chips send the hostnames of search results and AI citations while the chips and grade switches are on; from 1.0.17 a readings switch, on by default, sends one signed page reading a day (numbers, the hostname and the page address with the query removed; never in incognito; at most 40 a day) and only while the share and grade switches are also on. Earlier versions send nothing. **Our own machine layer for the agentic web:** [llms.txt](/llms.txt) · [llms-full.txt](/llms-full.txt) · [agents.md](/agents.md) · [SKILL.md](/SKILL.md) · [entitymap.json](/entitymap.json) · [media kit](/.well-known/media-kit.json) · [MCP server card](/.well-known/mcp/server-card.json) · [API catalog](/.well-known/api-catalog) · [OpenAPI](/openapi.json) · [robots.txt](/robots.txt) · [sitemap.xml](/sitemap.xml) · [security.txt](/.well-known/security.txt) — every one named in robots.txt, which is exactly what we check for on yours. **Pages:** [Certificates](/certificates) | **Registry:** [MCP: Operator](/registry/mcp/operator) · [MCP](/registry/mcp) · [AI policy](/registry/aipolicy) · [beget.ru](/registry/beget.ru) · [dimmittchevrolet.com](/registry/dimmittchevrolet.com) · [infralyte.in](/registry/infralyte.in) | **Glossary:** [Semantic cache](/glossary/semantic-cache) · [Entity-first content](/glossary/entity-first-content) · [Reduced motion](/glossary/reduced-motion) · [revocation delta](/glossary/revocation-delta) · [Sitemap directive](/glossary/sitemap-directive) [Contact](/contact) · [Partnerships](/partnerships) · [Terms of service](/terms) · [Refund policy](/refunds) · [Trust center](/trust) · [Subprocessors](/subprocessors) · [Changelog](/changelog) · [Report an error](/report-error)
Same body as a file: /blog/one-in-four-mcp-hosts-changed-its-tools-in-four-days.md · as data: /feed.json · what we tell agents site-wide: /llms.txt, /agents.md. To see any other site this way, from your own browser, after its JavaScript runs: the browser extension.