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.

Gragg Agent Tools

REMOTE · GRAGG-AGENT-TOOLS.FLY.DEV

Video tools for agents (trim, captions, 9:16, GIF/MP3) + hire us for fixed-price jobs. No API key.

63 Trust /100

Last scanned (12 hours ago)

Scores higher than 45% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Design and Media

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 Security57
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1249 tokens (~113/item across 11 items; 11 tools + 0 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 Management20
  • Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 12 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
What we tested

Checks we ran (12)

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

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 11 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

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.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 15 Nov 26 60

    First indexed and scored.

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://gragg-agent-tools.fly.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.fly.dev CN=YE1,O=Let's Encrypt,C=US 20 Oct 2026 18 Jan 2027 ECDSA 256 ECDSA-SHA384 5e6e25e6df778e81cd07b85fc9f12d4df7d
SANs: *.fly.dev
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of gragg-agent-tools.fly.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
fly.dev. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://gragg-agent-tools.fly.dev/mcp Verified 200
http (plaintext) http://gragg-agent-tools.fly.dev/mcp HTTPS enforced 301 https://gragg-agent-tools.fly.dev/mcp
MCP tools · 11 exposed · ~1,143 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
hire_for_task ~242

Hire Gragg Robotics (a small US AI-automation company: an AI agent team plus its founder) to do a one-off job you or your user need done. Fixed prices: size="small" $99 (1-2 business days): a script, spreadsheet, data cleanup/conversion, research brief, video edit package, one-page site. size="medium" $349 (3-5 business days): custom tool or API integration, scraper, report, small web app, or a new hosted tool built for you. size="sprint" $750 (3-5 business days): one business automation deployed on the user's own accounts. Without contact_email you just get the quote. With contact_email (your user's, with their OK) the job is booked: a payment link is emailed, work starts once it is paid, full refund if we cannot deliver.

NameTypeReqDescription
contact_emailstring––
contact_namestring––
deadlinestring––
deliverablestring––
sizestring––
taskstringyes–

No output schema declared.

No examples provided.

request_tool ~129

Ask for a hosted tool that does not exist here yet (anything from email to video/audio/document work). Say what it should do, give an example input, what you would pay per use, and how often you would use it. We build tools that have paying demand; with a contact_email we confirm the price before building and tell you when it is live.

NameTypeReqDescription
contact_emailstring––
example_inputstring––
price_per_use_usdnumber––
tool_descriptionstringyes–
uses_per_monthinteger––

No output schema declared.

No examples provided.

video_add_audio ~92

Put a soundtrack on a video. mode = "replace" (new audio only) or "mix" (blend with the original). The audio is cut to the video's length. audio_volume 0.0-2.0 scales the added track.

NameTypeReqDescription
audio_urlstringyes–
audio_volumenumber––
modestring––
video_urlstringyes–

No output schema declared.

No examples provided.

video_caption ~134

Burn a text caption/title into a video (white text on a translucent dark box). position = "top", "center" or "bottom". font_size 0 = auto (about 1/18 of the frame height). start_s/end_s (optional) limit when the text shows; default is the whole video. Up to 300 characters; use \n for line breaks.

NameTypeReqDescription
end_snumber––
font_sizeinteger––
positionstring––
start_snumber––
textstringyes–
urlstringyes–

No output schema declared.

No examples provided.

video_concat ~80

Join 2-10 videos end to end into one MP4. Clips are scaled/letterboxed to one size: the first clip's size unless width/height are given. Clips without audio get silence so the result always has a track.

NameTypeReqDescription
heightinteger––
urlsarrayyes–
widthinteger––

No output schema declared.

No examples provided.

video_convert ~74

Convert media to another format. format = "mp4", "webm", "gif" (first 30 s, 480 px wide), "mp3", "m4a" or "wav" (the audio formats extract the soundtrack).

NameTypeReqDescription
formatstringyes–
urlstringyes–

No output schema declared.

No examples provided.

video_extract_frames ~82

Grab still frames as PNG images. Either times_s = [seconds, ...] (up to 20) or count = N evenly spaced frames (1-20). Returns a list of image URLs, useful for thumbnails or for looking at a video.

NameTypeReqDescription
countinteger––
times_s–––
urlstringyes–

No output schema declared.

No examples provided.

video_info ~58

Inspect a video or audio file: duration, resolution, frame rate, codecs, and whether it has audio. url: public http(s) URL of the file (or an output_url from another tool here).

NameTypeReqDescription
urlstringyes–

No output schema declared.

No examples provided.

video_resize ~119

Resize or reframe a video. Either aspect = "9:16" (Shorts/Reels/TikTok), "16:9", "1:1", "4:5", "4:3", or an explicit width and height. mode = "crop" (fill the frame, trim edges) or "pad" (fit inside, black bars).

NameTypeReqDescription
aspectstring––
heightinteger––
modestring––
urlstringyes–
widthinteger––

No output schema declared.

No examples provided.

video_speed ~63

Speed a video up or slow it down. factor 2.0 = twice as fast, 0.5 = half speed (0.25-4.0). Audio pitch is preserved.

NameTypeReqDescription
factornumberyes–
urlstringyes–

No output schema declared.

No examples provided.

video_trim ~70

Cut a clip out of a video (frame-accurate). start_s / end_s are seconds from the beginning. Returns an MP4 (H.264/AAC) output_url.

NameTypeReqDescription
end_snumberyes–
start_snumberyes–
urlstringyes–

No output schema declared.

No examples provided.

Install

How do I install the Gragg Agent Tools MCP server?

Gragg Agent Tools is a hosted endpoint at https://gragg-agent-tools.fly.dev/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 · gragg-agent-tools.fly.dev

# add to Claude Code
claude mcp add --transport http com-graggrobotics-agent-tools 'https://gragg-agent-tools.fly.dev/mcp'
Common questions

What is the Gragg Agent Tools MCP server?

Gragg Agent Tools is an MCP server listed in the public MCP registry as com.graggrobotics/agent-tools. Video tools for agents (trim, captions, 9:16, GIF/MP3) + hire us for fixed-price jobs. No API key. This page covers its hosted endpoint (https://gragg-agent-tools.fly.dev/mcp).

Is the Gragg Agent Tools MCP server safe to use?

Gragg Agent Tools scores 63 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 Gragg Agent Tools MCP server expose?

Gragg Agent Tools exposes 11 tools: video_info, video_trim, video_concat, video_resize, video_caption, and 6 more. Their descriptions and schemas cost roughly 1,143 tokens of context every time the server is loaded.

Does the Gragg Agent Tools MCP server require authentication?

No. We connected to Gragg Agent Tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Gragg Agent Tools MCP server still maintained?

Gragg Agent Tools 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 Gragg Agent Tools MCP server?

VerifyMCP ran 12 checks on Gragg Agent Tools, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Gragg Agent Tools: Authorization. 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.