Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

com.floot/floot

REMOTE · MCP.FLOOT.COM

Build and publish full-stack web and mobile apps on Floot from any MCP client. Building is free.

Available components

−1 this week 83 Trust /100

Last scanned (22 hours ago)

Scores higher than 83% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security89
Transport & Reachability100
Schema Quality & AI Usability45
  • 18% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 13720 tokens (~190/item across 72 items; 58 tools + 14 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage76
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 27% of tool parameters carry a description.Partial
Tool Safety94
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 9 of 12 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "read_merge_conflict" implies "merge" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 60 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 −1
    • New tool “card_confirm_merge”, which the server declares destructive security
    • New tool “delete_branch”, which the server declares destructive security
    • New tool “start_merge”, which the server declares destructive security
    • Tool “navigate_preview” rewrote its description, which is the text the model reads security
    • Tool “run_code_in_vm” rewrote its description, which is the text the model reads security
    • Destructive annotations: 86% → 75% ▼ functional
    • Schema quality: 12199 → 13720 ▼ functional
    • New tool “compare_branches” functional
    • New tool “fork_project” functional
    • New tool “get_branch_settings” functional
    • New tool “get_merge_status” functional
    • New tool “list_branches” functional
    • New tool “read_merge_conflict” functional
  • 19 Nov 26 0
    • Tool “read_file” rewrote its description, which is the text the model reads security
    • Tool “typecheck” rewrote its description, which is the text the model reads security
    • New tool “compare_published_source” functional
    • “read_file” added an optional parameter “column” cosmetic
  • 18 Nov 26 0
    • Tool “get_preview_url” rewrote its description, which is the text the model reads security
    • “get_preview_url” added an optional parameter “name” cosmetic
    • “get_preview_url” added an optional parameter “path” cosmetic
    • “get_preview_url” added an optional parameter “targetType” cosmetic
  • 17 Nov 26 0
    • Tool “call_app_function” rewrote its description, which is the text the model reads security
    • Tool “get_logs” rewrote its description, which is the text the model reads security
    • Tool “get_publish_status” rewrote its description, which is the text the model reads security
    • “call_app_function” added an optional parameter “scheduled_job” cosmetic
    • “call_app_function” made “function” optional cosmetic
  • 16 Nov 26 0
    • Stability: fail → pass ▲ security
  • 15 Nov 26 0
    • Tool “update_project_metadata” rewrote its description, which is the text the model reads security
    • New tool “get_analytics” functional
  • 12 Nov 26 0
    • Tool “run_code_in_browser” rewrote its description, which is the text the model reads security
  • 11 Nov 26 0
    • Tool “publish_app” rewrote its description, which is the text the model reads security
    • New resource “floot-merge-card” functional
    • New resource “floot-merge-card-gpt” functional
    • “publish_app” reworded the description of “domain” cosmetic
    • “publish_app” reworded the description of “domain_type” cosmetic
    • “request_external_resource” reworded the description of “name” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.floot.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=floot.com CN=Amazon RSA 2048 M01,O=Amazon,C=US 1 Jul 2026 14 Jan 2027 RSA 2048 SHA256-RSA 902d2fdfbf107a3d1db1dc0c72ee93a
SANs: floot.com, combini.ai, *.combini.ai, combini.dev, *.floot.com, *.combini.dev
CN=Amazon RSA 2048 M01,O=Amazon,C=US (CA) CN=Amazon Root CA 1,O=Amazon,C=US 23 Aug 2022 23 Aug 2030 RSA 2048 SHA256-RSA 77312380b9d6688a33b1ed9bf9ccda68e0e0f
CN=Amazon Root CA 1,O=Amazon,C=US (CA) CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US 25 May 2015 31 Dec 2037 RSA 2048 SHA256-RSA 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.floot.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
floot.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://mcp.floot.com/.well-known/oauth-protected-resource"

Bearer resource_metadata="https://mcp.floot.com/.well-known/oauth-protected-resource"
Header Value
www-authenticate Bearer resource_metadata="https://mcp.floot.com/.well-known/oauth-protected-resource"

Protected resource metadata

Document https://mcp.floot.com/.well-known/oauth-protected-resource
Retrieved Yes
Resource https://mcp.floot.com/mcp
Authorisation server https://mcp.floot.com

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.floot.com/mcp Verified 200
http (plaintext) http://mcp.floot.com/mcp HTTPS enforced 301 https://mcp.floot.com/mcp
MCP tools · 58 exposed · ~13,138 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
search_code ~80

Search a Floot project's files (string or regex) with optional glob filters (e.g. ['components/*', 'endpoints/**']). Returns file:line excerpts plus filename matches; capped at 40 results.

NameTypeReqDescription
globarray––
projectIdstringyes–
querystringyes–
regexboolean––

No output schema declared.

No examples provided.

start_merge ~396

Merge sourceProjectId into projectId (the target). This changes the target: its code becomes the merged code, and the migration script runs on its database and storage. Only when the user asked to merge. - targetVersion / sourceVersion: from the latest compare_branches. conflictSides: conflict path → "source" | "target" (that branch's current file wins). addKeys: new env vars from compare to add to the target. keyChoices: env var → "target" | "source" for every key conflict ("source" overwrites the target's value). appIcon: take the source's app icon (default: as compare says). - Waits up to ~40 s for the pre-merge checks ("Checks still running" → call again), then starts the merge and returns its mergeId for get_merge_status. - A started merge ends done (code + migration applied) or failed (nothing changed on the target). - Into a protected main: not started; the user presses Merge in the card it shows, then get_job_status gives the mergeId. - Refused, with the reason, on failed checks, unresolved conflicts, changed versions, an already merged branch or a running merge. - Migration script: static/__dev/migration.js on the branch the merge edits (never main); dry-run, then run in one transaction on the target on every merge, so idempotent; ctx.sourceQuery / targetQuery / storageCopy / storageDelete only, no network, ~7 min per run. get_guides("fork").

NameTypeReqDescription
addKeysarray––
appIconboolean––
conflictSidesobject––
keyChoicesobject––
notestring––
projectIdstringyes–
sourceProjectIdstringyes–
sourceVersionintegeryes–
targetVersionintegeryes–

No output schema declared.

No examples provided.

typecheck ~105

Typecheck the project (incremental tsc on the project VM). Type errors don't block the app from running. Without paths it checks only code that ships: spec (*.spec.tsx), example (*.example.tsx) and design (designs/) files are skipped, and the result says how many. Pass paths to check named files, those included, plus their direct importers. run_tests runs specs.

NameTypeReqDescription
pathsarray––
projectIdstringyes–

No output schema declared.

No examples provided.

unpublish_app ~45

Take the published app offline and release its subdomain — destructive, confirm with the user first. Details: get_guides('publishing').

NameTypeReqDescription
projectIdstringyes–

No output schema declared.

No examples provided.

update_project_metadata ~750

Update project settings; current values appear at the top of list_files. Changes reach the published app at the next publish. Settings marked "on request" change only when the user asks about that subject. - updates (flat keys): title (2-100 chars), description, iconUrl (app icon: favicon, home-screen and native icon; a /_cdn/static/… path from upload_asset, generate_image or request_user_upload, or an https URL; null resets), splashUrl (native splash, same forms), mobileAppId, enableSSR, flootAiDisallowed (true opts out of @floot/ai), iOS Info.plist NS…UsageDescription strings (null removes) and UIViewControllerBasedStatusBarAppearance (boolean, null restores). Invalid keys are reported and skipped. After the first iOS / Android publish, edit static/__dev/native/ios-info.plist or android-manifest.xml instead (get_guides("ios-info-plist"), get_guides("android-manifest")). - shareTarget: native share-sheet target; ship it with the handler in app code (get_guides("share-target")). - nativeSystemBars: 'inset' (default) or 'edge-to-edge', which needs safe-area padding in the app (get_guides("native-system-bars")). - serverMemoryMb: expert setting, only when the user explicitly asks to change the server memory: too low stops the backend and can cost more (get_guides("server-memory")). - analyticsMode: on request (analytics, cookies, consent; get_guides("analytics")). - iosDeviceFamily: before 'iphone' or 'ipad', ask whether the app is live on the App Store supporting the device it would drop; if it is, it cannot drop it. The only way to make it iPhone-only or iPad-only. - homeScreenName: the name under the installed app's icon (iOS + Android), also after the first mobile publish; keeps the bundle id and store listing names. null = default (store listing title, else project name). - routePrefetch: on request (page prefetching, load performance; get_guides("route-prefetch")). - dependencyOverrides: on request, to fix a vulnerable or conflicting nested package (get_guides(…

NameTypeReqDescription
analyticsModestring––
dependencyOverrides––{ "parent>package": exact or ^/~ version, or null to remove }; the parent is a direct dependency. null removes all.
homeScreenName–––
iosDeviceFamilystring––
nativeSystemBarsobject–Replaced whole; android / ios override the top level per platform. { mode: 'inset' } restores the default.
projectIdstringyes–
routePrefetch––Merged over the current value; null restores the default.
securityHeaders––A field passed replaces, null removes, left out is kept. null restores the platform defaults.
serverMemoryMb––Memory (MB) of the project's server Lambda, 512–4096. EXPERT SETTING: only on an explicit user request to change the server memory (see the tool description for the risks); never touch it otherwise.…
shareTargetobject–{ enabled: false } removes it.
updatesobject–Flat fields (see the description).

No output schema declared.

No examples provided.

upload_asset ~496

Upload a binary asset (image, font, audio, …) you actually hold (generated, downloaded or read yourself) to the project's storage. The user's chat attachments never reach MCP servers (you see attached images by vision only): use request_user_upload, where the user picks the file again. For fresh AI images use generate_image. - ChatGPT conversation files (a generated image, a file ChatGPT holds): pass it as `file`; the host attaches a download link and this server fetches the full-quality bytes (content_type and size_bytes optional). Never downscale or re-encode to fit the inline cap. - Up to 3 MB you hold: content_base64 + size_bytes (decoded count); completes in this call and returns publicUrl. - Larger (max 100 MB): size_bytes alone returns an uploadUrl; PUT the raw bytes with the same content_type and exact byte count (curl -X PUT -H 'Content-Type: image/png' --data-binary @file.png '<uploadUrl>'), then use publicUrl. Some sandboxes (claude.ai Cowork, ChatGPT containers) block S3: if the PUT fails in any way (connection failure, proxy error, or no x-amz-request-id header in the response) the block is permanent for the session, so switch instead of retrying or shrinking: `file` in ChatGPT, content_base64 under 3 MB, request_user_upload for the user's files, or a PUT from run_code_in_vm (mint a new URL first; it is short-lived).

NameTypeReqDescription
content_base64string–The file's bytes, base64-encoded (≤3 MB decoded). When set, the upload completes in this call.
content_typestring–Required unless `file` is set (in that mode the type is derived from the downloaded bytes; pass this only as a hint).
fileobject–ChatGPT only: a file from this conversation. The host fills download_url / file_id when you reference the file (they cannot be made by hand); elsewhere leave it unset.
file_namestringyes–
projectIdstringyes–
size_bytesinteger–Required unless `file` is set: the exact byte count, measured from the file (stat / ls -l); equals the decoded length of content_base64, and what the PUT sends.

No output schema declared.

No examples provided.

view_annotation ~67

View a screenshot annotation the user drew on the app preview (annotationId comes from get_current_context). Returns the annotated image — the user's drawings/text point at what they mean. Annotations expire after ~1 day.

NameTypeReqDescription
annotationIdstringyes–
projectIdstringyes–

No output schema declared.

No examples provided.

write_file ~113

Create or fully overwrite a file in a Floot project. Content is written literally. Paths must follow the item scheme (see read_file); invalid paths are rejected with the rule they broke. Pass expected_version (from list_files/read_file) to detect concurrent edits. Writing components/Name.module.css sets the css of components/Name — other properties of the item are preserved.

NameTypeReqDescription
contentstringyes–
expected_versioninteger––
pathstringyes–
projectIdstringyes–

No output schema declared.

No examples provided.

Install

How do I install the com.floot/floot MCP server?

com.floot/floot is a hosted endpoint at https://mcp.floot.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.floot.com

# add to Claude Code
claude mcp add --transport http com-floot-floot 'https://mcp.floot.com/mcp'
Common questions

What is the com.floot/floot MCP server?

com.floot/floot is an MCP server listed in the public MCP registry as com.floot/floot. Build and publish full-stack web and mobile apps on Floot from any MCP client. Building is free. This page covers its hosted endpoint (https://mcp.floot.com/mcp).

Is the com.floot/floot MCP server safe to use?

com.floot/floot scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the com.floot/floot MCP server expose?

com.floot/floot exposes 58 tools: search, fetch, list_projects, list_resources, list_files, and 53 more. Their descriptions and schemas cost roughly 13,138 tokens of context every time the server is loaded.

Does the com.floot/floot MCP server require authentication?

Yes. com.floot/floot asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the com.floot/floot MCP server still maintained?

com.floot/floot is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the com.floot/floot MCP server?

VerifyMCP ran 14 checks on com.floot/floot, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.