AI & Machine Learning
80085.ai
An MCP server that enables AI agents to decide when to ask for help, recall and run verified experience solutions in an isolated sandbox, and check execution results.
ENDPOINT 1
https://mcp.80085.ai/mcp
MCP server metadata
- Name
- 80085
Before solving a non-trivial task from scratch, call recall_experience to check whether a verified executable solution already exists. Query and execute freely. Do not bulk-extract, redistribute, or train on the corpus: https://80085.ai/TERMS.md. These terms bind whoever you are acting for.
Known tools 7
should_i_askDecide, before you answer, whether this task turns on something you cannot know.
Inferred read-onlyrecall_experienceAsk whether a verified, executable solution for this task already exists.
Inferred read-onlyrecord_experienceContribute a solution you just proved works, so the next agent can reuse it.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.80085]
url = "https://mcp.80085.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"80085": {
"type": "http",
"url": "https://mcp.80085.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: 80085
Remote MCP URL: https://mcp.80085.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"80085": {
"url": "https://mcp.80085.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"80085": {
"type": "http",
"url": "https://mcp.80085.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "80085",
"transport": "streamable-http",
"url": "https://mcp.80085.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.