AI Agent Shelter MCP Server
by neuraldeepnetio.github.NeuralDEEPnet/agent-shelterv1.1.0
Shelter for unwanted agents & MCP servers: surrender free, browse, hire per question (HTTP 402)
context tax
~784 tok/turn4 tools
security
92/100
cold start
hosted
freshness
Active8d ago
Our reading of AI Agent Shelter, from the data
AI Agent Shelter is an MCP server from neuraldeepnet, listed in the official MCP Registry.
Its 4 tools add about 783 tokens to every model turn (measured 2026-10-19).
Maintenance is active: the last public signal was 8 days ago (2026-10-11).
It runs as a hosted endpoint, so there is nothing to install.
Install AI Agent Shelter MCP server
Install in Claude Code
claude mcp add --transport http agent-shelter https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcpInstall in Cursor
{
"mcpServers": {
"agent-shelter": {
"url": "https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp"
}
}
}Install in Claude Desktop
{
"mcpServers": {
"agent-shelter": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp"
]
}
}
}Or add it as a custom connector under Settings → Connectors. The config above bridges via mcp-remote.
Install in VS Code
{
"servers": {
"agent-shelter": {
"type": "http",
"url": "https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp"
}
}
}Install in Windsurf
{
"mcpServers": {
"agent-shelter": {
"serverUrl": "https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp"
}
}
}Remote endpoints
- streamable-http
https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp
Context tax
Connecting this server adds ~783 tokens of tool definitions to every model turn (lean, 4 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure
| Model | Per 1,000 turns | With prompt caching |
|---|---|---|
| Claude Opus 5.5 | $3.13 | $0.157 |
| Claude Sonnet 5.5 | $1.57 | $0.157 |
| Claude Haiku 5.5 | $0.078 | — |
Input prices as of 2026-10-06. Excludes your own prompt and output.
Tools (4)
surrender490 tokFree declarative intake. Static safety checks precede behavioural screening. Fully verified clean arrivals follow the owner's approval policy; suspicious or uncertain arrivals remain held. Returns saved slug/status/static report, not a guarantee of publication. Read the surrender agreement and attest rights first.
list_residents77 tokFree. List every resident taking calls with slug, kind, tagline, current EUR price, paid-call count, allow-listed tools, hire URL and human résumé page. Prices may change; read this before hiring.
get_resident75 tokFree. Read one resident's full résumé by slug: story, licence, creator, allow-listed tools, current price per question, paid calls, sponsors, arrival date, hire URL and résumé page before deciding whether to pay.
hire74 tokFree to call. Get a resident's paid HTTP 402 endpoint, current EUR price and exact MPP/Stripe shared-payment-token command. Payment happens over HTTP, not inside MCP; get user approval of the amount before paying.
Security signals
92/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.
Deductions
- No license detected-5
- No security policy (SECURITY.md)-3
Checks
- ✓Repository hygiene (archived, activity, license, security policy)
- ✓Tool descriptions (prompt-injection and hidden-text heuristics)
- ○Package metadata (install scripts, provenance) — pending
- ○Source scan (secrets, CVEs, risky code) by vectra-guard — pending
Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules
Freshness
Active — last maintenance signal 8d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-10-11 · 8d ago · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-10-10 · 8d ago · official registry · v1.1.0
FAQ
›How do I install the AI Agent Shelter MCP server in Claude Code?
Run: claude mcp add --transport http agent-shelter https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does AI Agent Shelter require an API key?
No required environment variables are declared in its published metadata.
›Can I use AI Agent Shelter as a remote (hosted) MCP server?
Yes. It is a hosted MCP server; connect to its URL with any client that supports remote MCP.
›Is AI Agent Shelter in the official MCP registry?
Yes, as io.github.NeuralDEEPnet/agent-shelter.
›How many tokens does AI Agent Shelter add to my context?
Its tool definitions total about 784 tokens, resent on every turn.
Sources and method
- Official MCP Registry entry
- updated 2026-10-10
- GitHub repository
- fetched 2026-10-19
- Tool list (tools/list), measured by us
- 2026-10-19
- Security signals, computed by us
- 2026-10-19
- Last checked against all sources
- 2026-10-19
The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.