Clawhard Studio MCP

A remote MCP server providing 15 tools from Clawhard Studio, enabling AI assistants to trim text for token limits, score writing and websites for AI habits, total AI subscriptions, split group costs, build event schedules, and translate vague design requests into precise briefs.

Visit Clawhard Studio

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Clawhard Studio

MCP endpoint (Streamable HTTP)

https://mcp.clawhard.com/mcp

Vendor documentation

What you can do with it

Trim long text to reduce token usage
Score writing for AI-sounding habits
Total AI subscription costs and overlaps
Split group expenses and settle up

Source and maintenance

Vendor evidenceRegistry 1.2.0

mcp-registry: com.clawhard/studio@1.2.0 Project website

Protocol and capabilities

Server: com.clawhard/studio 1.0.0
MCP protocol: 2025-06-18
Tools: 15 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Clawhard Studio tools. Use tokendiet_trim_text to shrink long text/logs before reuse, tells_score_text / tells_fix_text to check or clean writing that sounds like AI, slopscore_check_site to score a public website for AI-made design habits, aitab_total / aitab_list_plans to total AI subscriptions, halves_settle_up / halves_create_group to split shared costs, runsheet_create / runsheet_list_templates for event day schedules, and lingo_translate / lingo_brief / lingo_list_terms to turn vague design requests into precise design terms and a brief for a coding agent. Share returned open_url / group_url / view_url links with the user. Never share runsheet edit_url publicly.

Tools

15 advertised

tokendiet_trim_text — Trim junk out of text before pasting it into an AI chat

Advertised by the server during the last successful anonymous check.

Advertised read-only

Shrinks a prompt, chat, log, stack trace, JSON dump or code paste so it uses fewer tokens: removes base64 and data blobs, minifies JSON, shortens stack traces, squashes repeated log lines, strips code comments and link tracking parameters, and collapses whitespace. Optionally drops pleasantries and markdown. Returns the trimmed text and how much was saved. Token numbers here are rough estimates (about 4 characters per token); the website shows exact counts.

tokendiet_trim_text input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to trim (up to 200,000 characters)."
    },
    "rules": {
      "type": "array",
      "items": {
        "enum": [
          "blobs",
          "json",
          "traces",
          "repeats",
          "comments",
          "urls",
          "space",
          "polite",
          "markdown"
        ],
        "type": "string"
      },
      "description": "Rules to apply. Default: blobs, json, traces, repeats, comments, urls, space. Also available: polite, markdown."
    }
  }
}

tokendiet_trim_text annotations

{
  "title": "Trim junk out of text before pasting it into an AI chat",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

slopscore_check_site — Score a website for AI-made design habits

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

Fetches a public web page and its main stylesheets and scripts once, then scores it from 0 (hand-made feel) to 100 (certified slop) against 19 design and copy habits that make a site look AI-made (purple gradients, gradient headlines, glow blobs, glassmorphism, default fonts, untouched component kits, icon card grids, buzzwords, template headlines, vague social proof, placeholder testimonials, app-builder leftovers, em dashes and more). Returns each tell found with how to fix it.

slopscore_check_site input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Public website address, for example example.com or https://example.com/pricing"
    }
  }
}

slopscore_check_site annotations

{
  "title": "Score a website for AI-made design habits",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

aitab_list_plans — List AI subscription plans and list prices

Advertised by the server during the last successful anonymous check.

Advertised read-only

Lists the AI subscription plans AI Tab knows (chat assistants, coding tools, image and video, voice and music, work) with their USD list prices and the plan keys to pass to the total tool.

aitab_list_plans input schema

{
  "type": "object",
  "properties": {}
}

aitab_list_plans annotations

{
  "title": "List AI subscription plans and list prices",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

aitab_total — Total what you pay for AI subscriptions

Advertised by the server during the last successful anonymous check.

Advertised read-only

Adds up a list of AI subscriptions and returns the monthly, yearly and daily total, where the user is paying twice for the same thing (overlaps), what could be cut and how much that saves, plus a link that opens the shareable receipt. Use plan keys from the plans tool, for example chatgpt.plus, claude.pro, cursor.pro. Append ":y" to a key for yearly billing.

aitab_total input schema

{
  "type": "object",
  "required": [
    "plans"
  ],
  "properties": {
    "plans": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Plan keys, e.g. [\"chatgpt.plus\",\"claude.pro\",\"cursor.pro\"]. In a GET query use a comma-separated list."
    },
    "billing": {
      "enum": [
        "monthly",
        "yearly"
      ],
      "type": "string",
      "description": "Which total the shared receipt shows first. Default monthly."
    }
  }
}

aitab_total annotations

{
  "title": "Total what you pay for AI subscriptions",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

tells_score_text — Score writing for AI-sounding habits

Advertised by the server during the last successful anonymous check.

Advertised read-only

Checks a piece of writing for the habits that make people think a chatbot wrote it (em dashes, words like "delve", assistant filler like "I hope this helps", "it's not X, it's Y", fake suspense, stiff transitions, markdown leftovers, emoji bullets, rule of three, same-length sentences). Returns a 0-100 bot-o-meter score, a verdict and the tells found. Style habits only. Not an AI detector and not proof of who wrote the text.

tells_score_text input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The writing to check (up to 60,000 characters)."
    }
  }
}

tells_score_text annotations

{
  "title": "Score writing for AI-sounding habits",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

tells_fix_text — Remove the easy AI-sounding habits from writing

Advertised by the server during the last successful anonymous check.

Advertised read-only

Rewrites the easy tells: swaps em dashes for commas, chatbot words for plain ones, strips assistant filler, markdown stars and emoji bullets, fixes stiff transitions. Habits that need a human rewrite ("it's not X, it's Y", fake suspense, rule of three) are listed but left alone. Returns the fixed text, the before and after score and what remains.

tells_fix_text input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The writing to clean up (up to 60,000 characters)."
    },
    "categories": {
      "type": "array",
      "items": {
        "enum": [
          "dash",
          "buzz",
          "filler",
          "frame",
          "reveal",
          "trans",
          "md",
          "emoji",
          "three",
          "rhythm"
        ],
        "type": "string"
      },
      "description": "Optional: only fix these categories. Default: every auto-fixable category."
    }
  }
}

tells_fix_text annotations

{
  "title": "Remove the easy AI-sounding habits from writing",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

runsheet_list_templates — List run sheet templates

Advertised by the server during the last successful anonymous check.

Advertised read-only

Lists the starter run sheets (wedding, conference, photo shoot, blank) with their default times, so you can pick one or adapt it before creating a run sheet.

runsheet_list_templates input schema

{
  "type": "object",
  "properties": {}
}

runsheet_list_templates annotations

{
  "title": "List run sheet templates",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

runsheet_create — Create a live day-of schedule (run of show)

Advertised by the server during the last successful anonymous check.

Open-world

Creates a Runsheet: a live, shareable schedule for an event day (wedding, shoot, conference, any timed run of show). Start from a template or send your own items. Returns a view-only link for guests and vendors and a private edit link for the planner. Keep the edit link secret: anyone with it can change the schedule.

runsheet_create input schema

{
  "type": "object",
  "properties": {
    "date": {
      "type": "string",
      "description": "YYYY-MM-DD"
    },
    "name": {
      "type": "string",
      "description": "Event name."
    },
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "time",
          "title"
        ],
        "properties": {
          "who": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Vendors or roles on this slot"
          },
          "time": {
            "type": "string",
            "description": "Start, 24-hour HH:MM"
          },
          "title": {
            "type": "string"
          },
          "where": {
            "type": "string"
          },
          "duration_minutes": {
            "type": "integer"
          }
        }
      },
      "maxItems": 200,
      "description": "Schedule slots."
    },
    "template": {
      "enum": [
        "wedding",
        "conf",
        "shoot",
        "blank"
      ],
      "type": "string",
      "description": "Starter schedule. Ignored if items are given."
    },
    "timezone": {
      "type": "string",
      "description": "IANA time zone, e.g. America/New_York. Default UTC."
    }
  }
}

runsheet_create annotations

{
  "title": "Create a live day-of schedule (run of show)",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}

halves_settle_up — Work out who owes whom, in the fewest payments

Advertised by the server during the last successful anonymous check.

Advertised read-only

Given a group of people and the expenses (who paid, how much, who shared it), returns each person's net balance and the smallest set of payments that squares everyone up. Splits equally by default, or by exact amounts. Stateless: nothing is saved. Use create_group instead to make a shared link people can keep adding to.

halves_settle_up input schema

{
  "type": "object",
  "required": [
    "people",
    "expenses"
  ],
  "properties": {
    "people": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Names of everyone in the group (2 to 40, unique)."
    },
    "currency": {
      "type": "string",
      "description": "ISO currency code, default USD."
    },
    "expenses": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "amount",
          "paid_by"
        ],
        "properties": {
          "what": {
            "type": "string"
          },
          "exact": {
            "type": "object",
            "description": "Optional exact amount per person (must add up to amount). Overrides split_between.",
            "additionalProperties": {
              "type": "number"
            }
          },
          "amount": {
            "type": "number",
            "description": "Total in normal units, e.g. 45.50"
          },
          "paid_by": {
            "type": "string"
          },
          "split_between": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Who shared it. Default: everyone, equally."
          }
        }
      },
      "description": "What was paid."
    },
    "payments": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "from",
          "to",
          "amount"
        ],
        "properties": {
          "to": {
            "type": "string"
          },
          "from": {
            "type": "string"
          },
          "amount": {
            "type": "number"
          }
        }
      },
      "description": "Payments already made between people to settle up."
    }
  }
}

halves_settle_up annotations

{
  "title": "Work out who owes whom, in the fewest payments",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

halves_create_group — Create a shared expense group link

Advertised by the server during the last successful anonymous check.

Open-world

Creates a Halves group and returns a link anyone can open (no sign-up) to add and fix expenses and see who owes whom. Optionally pre-loads expenses. Anyone who has the link can edit the group, so share it only with the people in it. Groups are kept for about 400 days after the last change.

halves_create_group input schema

{
  "type": "object",
  "required": [
    "people"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Group name, e.g. \"Lisbon trip\"."
    },
    "people": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Names (2 to 40)."
    },
    "currency": {
      "type": "string",
      "description": "Main currency, default USD."
    },
    "expenses": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Optional starting expenses (up to 50), same shape as the settle tool."
    }
  }
}

halves_create_group annotations

{
  "title": "Create a shared expense group link",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}

lingo_list_terms — List design vocabulary terms

Advertised by the server during the last successful anonymous check.

Advertised read-only

Lists the design vocabulary Lingo knows: 36 named looks in six groups (layout, type, color, shape, motion, style), each with a plain-English meaning and the exact wording and values to give an AI coding agent, plus the vague phrases Lingo can decode (like "make it pop").

lingo_list_terms input schema

{
  "type": "object",
  "properties": {}
}

lingo_list_terms annotations

{
  "title": "List design vocabulary terms",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

lingo_translate — Translate a vague design request into design terms

Advertised by the server during the last successful anonymous check.

Advertised read-only

Turns a vague design request ("make it pop", "it looks cheap", "too busy", "less AI-looking") into what designers usually mean by it and the specific design terms and values to use instead. Returns a ready-to-paste design brief and a link that opens it in Lingo.

lingo_translate input schema

{
  "type": "object",
  "required": [
    "phrase"
  ],
  "properties": {
    "phrase": {
      "type": "string",
      "description": "The vague request in plain words, e.g. \"it feels cheap and too busy\"."
    },
    "avoid_ai_look": {
      "type": "boolean",
      "description": "Add rules that steer away from the generic AI-made look. Default true."
    }
  }
}

lingo_translate annotations

{
  "title": "Translate a vague design request into design terms",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

lingo_brief — Write a design brief from chosen terms

Advertised by the server during the last successful anonymous check.

Advertised read-only

Builds a precise design brief (markdown) from Lingo term ids and/or vague phrases, ready to paste into an AI coding agent or a project rules file. Conflicting picks (for example sharp and soft corners) keep the last one. Includes optional "don't look AI-made" rules and a link that opens the brief in Lingo.

lingo_brief input schema

{
  "type": "object",
  "properties": {
    "say": {
      "type": "string",
      "description": "Optional vague request to decode and include, e.g. \"more premium\"."
    },
    "terms": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Term ids from the terms tool, e.g. [\"airy\",\"display\",\"accent\",\"soft\"]. In a GET query use a comma-separated list."
    },
    "avoid_ai_look": {
      "type": "boolean",
      "description": "Add rules that steer away from the generic AI-made look. Default true."
    }
  }
}

lingo_brief annotations

{
  "title": "Write a design brief from chosen terms",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

fluff_check_text — Score how much of a text is fluff

Advertised by the server during the last successful anonymous check.

Advertised read-only

Checks a memo, email, post, report or AI-written draft for fluff: pleasantries and throat-clearing, stock openers ("in today's fast-paced world"), padding ("it's important to note that"), buzzwords (leverage, synergy, robust), hedges, vague claims and sentences that repeat an earlier one. Returns a 0-100 fluff percentage, a verdict, every flagged sentence with the reason, the most used filler phrases, and the gist (only the lines that say something, with padding phrases trimmed). Rule-based wording check, not a fact check; it never invents text.

fluff_check_text input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to check (up to 60,000 characters)."
    }
  }
}

fluff_check_text annotations

{
  "title": "Score how much of a text is fluff",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

fluff_gist_text — Cut a text down to the lines that say something

Advertised by the server during the last successful anonymous check.

Advertised read-only

Returns the gist of a text: drops sentences that are pure filler, buzzwords, pleasantries or repeats, and trims padding phrases ("in order to" becomes "to", "it's important to note that" is removed) from the rest. Keeps the author's own words and order, invents nothing. Also returns the fluff percentage and how many words were cut.

fluff_gist_text input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to cut down (up to 60,000 characters)."
    }
  }
}

fluff_gist_text annotations

{
  "title": "Cut a text down to the lines that say something",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 220 ms
95th percentile latency: 220 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 8:06 AM UTC · probe · passed · 220 ms · metadata changed · 15 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http clawhard-studio-mcp https://mcp.clawhard.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add clawhard-studio-mcp --url https://mcp.clawhard.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable clawhard-studio-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "clawhard-studio-mcp": {
      "url": "https://mcp.clawhard.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "clawhard-studio-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.clawhard.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start clawhard-studio-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "clawhard-studio-mcp": {
      "type": "http",
      "url": "https://mcp.clawhard.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http clawhard-studio-mcp https://mcp.clawhard.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "clawhard-studio-mcp": {
      "url": "https://mcp.clawhard.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "clawhard-studio-mcp": {
      "serverUrl": "https://mcp.clawhard.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Clawhard Studio MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 4,207

Do you run Clawhard Studio MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing

Clawhard Studio MCP

Endpoint and access

What you can do with it

Source and maintenance

Protocol and capabilities

Server-provided instructions

Tools

Prompts

Resources

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other productivity and knowledge servers

Do you run Clawhard Studio MCP?