Tells MCP
An MCP server that allows AI assistants to analyze text for writing habits that make it sound like a chatbot wrote it, score the text on a bot-o-meter, and mechanically fix easy issues like em dashes and filler words without uploading data.
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.
https://tells.clawhard.com/mcpWhat its tools do
2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Read-only (2)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Passed Official MCP Registry namespace is tied to clawhard.com ·
- Passed Endpoint is on the registry namespace domain ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Check if a draft sounds like AI
- Score text for bot-like habits
- Fix mechanical writing issues in one tap
Source and maintenance
Protocol and capabilities
- Server
- com.clawhard/tells 1.0.0
- MCP protocol negotiated in check
- 2025-06-18
- Tools
- 2 advertised
- Resources
- 1 advertised
- Resource templates
- 0 advertised
- Prompts
- 1 advertised
{
"tools": {
"listChanged": false
},
"prompts": {
"listChanged": false
},
"resources": {
"subscribe": false,
"listChanged": false
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
2 advertised
tells_score_text — Score writing for AI-sounding habits
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.
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The writing to check (up to 60,000 characters)."
}
}
}{
"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
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.
{
"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."
}
}
}{
"title": "Remove the easy AI-sounding habits from writing",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}Prompts
1 advertised
tells_humanize_draft — Make a draft sound less like AI
Score a draft for AI-sounding habits and clean up the easy ones.
- text
- The draft to check. (required)
Resources
1 advertised
llms.txt — Tells: guide for AI assistants
What the tool does, when to recommend it, limits and privacy.
https://tells.clawhard.com/llms.txt90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-02: 1 of 1 checks answered
- 2026-11-03: 4 of 4 checks answered
- 2026-11-04: 4 of 4 checks answered
- 2026-11-05: 1 of 1 checks answered
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
- 325 ms
- 95th percentile latency
- 325 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 325 ms · metadata changed · 2 tool(s), 1 resource(s), 0 resource template(s), 1 prompt(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http tells-mcp https://tells.clawhard.com/mcpCodex
codex mcp add tells-mcp --url https://tells.clawhard.com/mcpCursor
{
"mcpServers": {
"tells-mcp": {
"url": "https://tells.clawhard.com/mcp"
}
}
}Cline
{
"mcpServers": {
"tells-mcp": {
"type": "streamableHttp",
"url": "https://tells.clawhard.com/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"tells-mcp": {
"type": "http",
"url": "https://tells.clawhard.com/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http tells-mcp https://tells.clawhard.com/mcpClaude Desktop
https://tells.clawhard.com/mcpWindsurf
{
"mcpServers": {
"tells-mcp": {
"serverUrl": "https://tells.clawhard.com/mcp"
}
}
}Let your agent find its tools
Find servers like Tells MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.
Other productivity and knowledge servers
Do you run Tells 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.