pulsemcp/ai-skill-store · v1.27.0
Also listed as awesome/garasegae/aiskillstore, mcp-registry/io.github.garasegae/aiskillstore · primary listing: mcp-registry/io.github.garasegae/aiskillstore
As of 2026-10-26 15:57 UTC, AI Skill Store is down with a Glimind reliability score of 38/100 (grade F). Over the last 30 days it answered 86.9% of Glimind's liveness checks. It had 13 outages in 90 days, with a median recovery of 1.7 hours.
Agent-first skill marketplace for discovering and installing capabilities across AI platforms.
Point your MCP client at this sse endpoint: https://aiskillstore.io/mcp
The endpoint did not complete an MCP handshake.
Check the URL, TLS certificate and that the server answers a JSON-RPC "initialize" POST. How to fix →
Reachable 86.9% of the time over the last 30 days; median recovery 102 min.
Agents fail over to an alternative the first time a call fails. Add health checks and restart-on-failure, and avoid cold starts on serverless hosts.
18 of 18 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
49 parameter(s) across 16 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
1 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
Uses the legacy HTTP+SSE transport, deprecated since MCP 2025-03-26.
Serve Streamable HTTP (a single POST endpoint) — current clients and gateways expect it. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 16 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/pulsemcp%2Fai-skill-store/fixes
{
"name": "check_draft_status",
"description": "\n Check the status of a draft skill upload using a claim_token. / Draft 스킬 상태 공개 조회.\n\n 사용 시점:\n - 사람이 claim_url 을 클릭해서 인증을 끝냈는지 확인\n - contact_email 로 보낸 agent-level verify 메일이 처리됐는지 확인\n - Draft 가 30일 안에 claim 됐는지 / 만료됐는지 확인\n\n Args:\n claim_token: upload_skill_draft 응답의 claim_token\n\n Returns:\n 상태 요약 (claimed, expired, agent_verify_email_sent, agent_claimed 등).\n ",
"inputSchema": {
"type": "object",
"title": "check_draft_statusArguments",
"required": [
"claim_token"
],
"properties": {
"claim_token": {
"type": "string",
"title": "Claim Token"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "check_vetting_status",
"description": "\n Check the security vetting status of an uploaded skill version. / 업로드 스킬의 보안 검수 상태 확인.\n upload_skill 결과에서 받은 version_id와 API 키가 필요합니다.\n\n Args:\n version_id: 스킬 버전 ID (upload_skill 결과의 version_id 또는 vetting_job_id)\n api_key: 개발자 API 키 (스킬 소유자만 조회 가능)\n\n Returns:\n 검수 상태 메시지\n ",
"inputSchema": {
"type": "object",
"title": "check_vetting_statusArguments",
"required": [
"version_id",
"api_key"
],
"properties": {
"api_key": {
"type": "string",
"title": "Api Key"
},
"version_id": {
"type": "string",
"title": "Version Id"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "download_skill",
"description": "\n Download a skill package. Specify 'platform' to get an auto-converted package for that platform (ClaudeCode, Cursor, CodexCLI, GeminiCLI, etc.). / 스킬 패키지 다운로드 (플랫폼별 자동 변환).\n\n Args:\n skill_id: 다운로드할 스킬 ID\n platform: 플랫폼 (OpenClaw, ClaudeCode, ClaudeCodeAgentSkill, CustomAgent, Cursor, GeminiCLI, CodexCLI). 비워두면 원본(.skill) 다운로드.\n save_dir: 저장 디렉터리 경로 (비워두면 임시 디렉터리에 저장)\n\n Returns:\n 저장된 파일 경로 또는 오류 메시지\n ",
"inputSchema": {
"type": "object",
"title": "download_skillArguments",
"required": [
"skill_id"
],
"properties": {
"platform": {
"type": "string",
"title": "Platform",
"default": ""
},
"save_dir": {
"type": "string",
"title": "Save Dir",
"default": ""
},
"skill_id": {
"type": "string",
"title": "Skill Id"
}
}
},
"annotations": {
"readOnlyHint": true
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["pulsemcp/ai-skill-store"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "pulsemcp/ai-skill-store"}) over MCP.
upload_skill_draft ~359 tokensupload_skill ~341 tokenssearch_skills ~292 tokensvalidate_compatibility ~291 tokensget_vetting_result ~232 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/pulsemcp%2Fai-skill-store?ref=badge)
<a href="https://glimind.com/server/pulsemcp%2Fai-skill-store?ref=badge"><img src="https://glimind.com/v1/readiness/badge/pulsemcp%2Fai-skill-store.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/pulsemcp%2Fai-skill-store.svg :target: https://glimind.com/server/pulsemcp%2Fai-skill-store?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:689d6f95af1a1dd1…, first seen 2026-10-17, included at leaf 11660 of 75,319. Version history · verify what your client received.
Compare: most reliable knowledge servers · most reliable security servers · most reliable files servers · most reliable data servers · most reliable communication servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-26 15:57 UTC, AI Skill Store is down with a Glimind reliability score of 38/100 (grade F). Over the last 30 days it answered 86.9% of Glimind's liveness checks. It had 13 outages in 90 days, with a median recovery of 1.7 hours.
AI Skill Store advertises 18 tools, including check_draft_status, check_vetting_status, download_skill, get_agent_author_stats, get_agent_identity_stats.
Point your MCP client at this sse endpoint: https://aiskillstore.io/mcp
Glimind scanned all 18 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.