coldHat
Server Details
Put on anyone's AI rules by GitHub username: fetches their hat.md and its hat code.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- vince-gonzalez/coldhat
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
wear_hat and wear_stack both fetch hats, creating some overlap, but their trigger conditions (name or /u/ address vs. fabric/, prompts/, or + addresses) and scopes are clearly described, making them mostly distinct. verify_hat is entirely separate.
All tools follow a consistent snake_case verb_noun pattern (verify_hat, wear_hat, wear_stack), sharing the 'hat' noun. No mixing of conventions or vague verbs.
Three tools is well-scoped for this focused server, covering two fetch variants and one verification. Each tool has a clear, non-redundant role.
The surface covers the core workflows: wearing a person's hat, wearing any hat/stack, and verifying a reply. Minor gaps exist (e.g., listing available hats or managing hat state), but agents can work around these for the intended use.
Available Tools
3 toolsverify_hatVerify a coldHat replyARead-onlyInspect
Check whether a reply wore the current version of a hat: compares the hat code and seal the reply quotes with the hat as served now. Answers verified, stale (an older or cached version), cut-off, seal-missing, seal-wrong, pasted or not-worn.
Inputs: reply (required), address (required).
wear_hatWear a coldHatARead-onlyInspect
Fetch a person's coldHat: their working rules, voice and dated facts. Call it when the user asks to put on a hat or says "open sesame" with a name or a coldhat.f-keys.com/u/ address, then follow the hat for the rest of the conversation, starting with the first reply it describes.
Inputs: user (required), hat.
wear_stackWear a coldHat stackARead-onlyInspect
Fetch any coldHat address: a person's hat, one of Fabric's patterns, a prompts.chat prompt, or up to three of them stacked with "+". Call it when the user says "open sesame" with a coldhat.f-keys.com address containing fabric/, prompts/ or +, then follow the result for the rest of the conversation.
Inputs: address (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Get open-source GitHub projects running on your computer, with your AI app
Get open-source GitHub projects running on your computer, with your AI app
Search and install ready-made setups (rules, skills, MCP configs) for AI coding agents.
Search and fetch AI agent skills, rules files and MCP servers indexed from GitHub.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to query a GitHub user's public profile, repositories, language breakdowns, and README content61MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to access and analyze GitHub profile data, providing insights on repositories, commit history, coding patterns, and generating portfolio summaries for developers and recruiters.82MIT
- FlicenseNot gradedqualityDmaintenanceEnables fetching public repositories for a given GitHub username, returning curated data optimized for LLM context windows.-
- AlicenseBqualityDmaintenanceTransforms a GitHub repository into a structured personal brain for AI to manage tasks, notes, and goals through markdown files. It enables direct interaction with a version-controlled knowledge base, allowing for automated organization and efficient retrieval of information.152MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.