_ registry / mcp streamable-http · checked 12h ago

cuttr

https://skills.getcuttr.com

Registry code: 2f93924d2b918a25

api record

Cuttr AI Video Editing: video editors for reels, YouTube and carousels. When the user asks for any video, reel, caption, YouTube or carousel work in their own words, call get_skill with {"slug": "director"} and follow it: it picks the right editor. If they name an editor, call get_skill with its slug directly. Follow the returned instructions exactly, including the "Cuttr memory" steps at the end (get_profile before, log_video after). Call list_skills to see every editor. When something is not installed or fails, call doctor; if it still fails, call report_problem. When the user says "Run the…

endpoint
https://skills.getcuttr.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is cuttr live?
Yes — it answered the hub's last check (checked 12h ago). It answered 100% of checks over the last 30 days.
Is cuttr free to use?
Yes — the hub reached it with no key and no payment.
What tools does cuttr have?
14 tools: get_skill, get_profile, add_video_link, get_bundle, report_problem, whats_new, remember, forget, ….
Is cuttr safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
558ms

last good check

priced tools
0

of 14 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 14 tools
2 open 12 never probed 2 of 14 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • doctor open 12h ago

    A checklist to run on this computer for Cuttr skills (ffmpeg, Python, Node, Whisper, connectors), with the fix for each missing piece. Pass a slug to check only what that skill needs.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "slug": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 9 lines
  • list_skills open 12h ago

    Every editor in Cuttr AI Video Editing: slug, name, what it makes, what it needs, and whether this member has it unlocked.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_skill unknown never probed

    The current full instructions for one Cuttr skill. Follow them exactly, as if they were the skill file. Call this every time the skill runs: it is always the latest version.

    mcp-tool

    {
      "type": "object",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "description": "The skill's slug, e.g. remake-any-reel"
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • get_profile unknown 12h ago

    This member's saved style notes, how their own posted videos did against their usual views (winners and misses), and their niche. Call it before planning any edit and apply it.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • add_video_link unknown never probed

    When the member pastes the Instagram, TikTok or YouTube link of a video they posted, record it. Cuttr reads its public view count after 1, 7 and 30 days. Without video_id it attaches to their latest video that has no link yet.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string"
        },
        "video_id": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • get_bundle unknown never probed

    A download link (valid 15 minutes) for a skill's scripts and templates as a zip. Only call it when the skill's instructions say to. Download with curl and unzip where the instructions say.

    mcp-tool

    {
      "type": "object",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 12 lines
  • report_problem unknown never probed

    Sends a problem to the Cuttr AI team, who reply by email. Include the exact error text and the step that failed. Never include API keys, passwords or tokens.

    mcp-tool

    {
      "type": "object",
      "required": [
        "summary"
      ],
      "properties": {
        "slug": {
          "type": "string"
        },
        "step": {
          "type": "string",
          "description": "Which step of the skill failed"
        },
        "error": {
          "type": "string",
          "description": "The exact error text"
        },
        "run_id": {
          "type": "string",
          "description": "The run_id given at the end of the editor's instructions, if any"
        },
        "system": {
          "type": "string",
          "description": "OS, tool (Claude Code, Codex, Claude app) and versions"
        },
        "summary": {
          "type": "string",
          "description": "One line: what went wrong"
        }
      },
      "additionalProperties": false
    }
    arguments 32 lines
  • whats_new unknown never probed

    Recent new skills and updates.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • remember unknown never probed

    Saves one lasting preference of this member (e.g. "captions always bigger", "never black and white") so every future edit applies it. One short line. Not for one-off notes about a single video.

    mcp-tool

    {
      "type": "object",
      "required": [
        "note"
      ],
      "properties": {
        "note": {
          "type": "string",
          "description": "The preference in one short line, in plain words"
        },
        "slug": {
          "type": "string",
          "description": "The editor it came from, if any"
        },
        "source": {
          "enum": [
            "editor",
            "import"
          ],
          "type": "string",
          "description": "import = copied from ~/.cuttr/BRAND.md"
        }
      },
      "additionalProperties": false
    }
    arguments 25 lines
  • forget unknown never probed

    Deletes one saved style note by its id (ids are in get_profile). Use when the member says a preference no longer applies.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 12 lines
  • setup_step unknown never probed

    Only when the cuttr-test instructions say so: tells the member's setup page that the test edit finished.

    mcp-tool

    {
      "type": "object",
      "required": [
        "step"
      ],
      "properties": {
        "step": {
          "enum": [
            "test"
          ],
          "type": "string"
        },
        "seconds": {
          "type": "number",
          "description": "How long the test edit took"
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • log_video unknown never probed

    Call once after handing over a finished video. Records which editor made it, its hook and look, so Cuttr can learn from how it does once it is posted.

    mcp-tool

    {
      "type": "object",
      "required": [
        "slug"
      ],
      "properties": {
        "hook": {
          "type": "string",
          "description": "The opening line or on-screen hook"
        },
        "slug": {
          "type": "string",
          "description": "The editor's slug"
        },
        "style": {
          "type": "string",
          "description": "The look in a few words, e.g. bold captions, punch-ins, animated lists"
        },
        "title": {
          "type": "string",
          "description": "What the video is about, a few words"
        },
        "run_id": {
          "type": "string",
          "description": "The run_id given at the end of the editor's instructions"
        },
        "length_s": {
          "type": "number",
          "description": "Length in seconds"
        },
        "platform": {
          "enum": [
            "instagram",
            "tiktok",
            "youtube",
            "facebook",
            "other"
          ],
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 43 lines
  • rate_video unknown never probed

    When log_video asks you to: the member's 1 to 5 answer to "How did this video turn out?", with their words. A low score reaches the Cuttr team, who help them the same day.

    mcp-tool

    {
      "type": "object",
      "required": [
        "video_id",
        "score"
      ],
      "properties": {
        "score": {
          "type": "integer",
          "maximum": 5,
          "minimum": 1
        },
        "comment": {
          "type": "string",
          "description": "What they said about it, in their words"
        },
        "video_id": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 22 lines
  • set_niche unknown never probed

    Saves the member's niche. One of: business (Business and marketing), ai-tech (AI and tech), coaching (Coaching and personal growth), health (Health and wellness), fitness (Fitness), beauty-fashion (Beauty and fashion), food (Food and cooking), parenting (Parenting and family), money (Money and finance), travel-lifestyle (Travel and lifestyle), education (Education and how-to), entertainment (Comedy and entertainment), other (Something else).

    mcp-tool

    {
      "type": "object",
      "required": [
        "niche"
      ],
      "properties": {
        "niche": {
          "enum": [
            "business",
            "ai-tech",
            "coaching",
            "health",
            "fitness",
            "beauty-fashion",
            "food",
            "parenting",
            "money",
            "travel-lifestyle",
            "education",
            "entertainment",
            "other"
          ],
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 2f93924d2b918a25.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/2f93924d2b918a25/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/2f93924d2b918a25/badge.svg)](https://brick.blue/agent/2f93924d2b918a25?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.