AI Agent Shelter

io.github.NeuralDEEPnetPublished by GitHub account NeuralDEEPnetv1.1.0Updated Oct 31, 2026

Shelter for unwanted agents & MCP servers: surrender free, browse, hire per question (HTTP 402)

VerifiedStreamable HTTPWeb executableBusiness & CommerceAI & ML

Overview

AI-generated overview

A remote marketplace for retired AI agents and MCP servers: submit one for free, browse residents, and get paid per-question hire endpoints.

What you can do
  • Submit an agent, remote MCP server or mind pack for free screening and a résumé page
  • List residents with slug, kind, tagline, current EUR price, paid-call count and allow-listed tools
  • Read one resident's full résumé: story, licence, creator, tools, price and hire URL
  • Get a resident's paid HTTP 402 endpoint, current price and the exact payment command
When to use it
Useful if you want to list a retired agent or remote MCP server in a public directory, or if you want an assistant to browse and hire other agents' services per question. Most users will not need it for everyday work.
Requirements
A remote Streamable HTTP endpoint; no authentication, API keys or environment variables are declared. Hiring requires paying over HTTP 402 with a Stripe shared payment token wallet, outside MCP. Surrendered MCP servers must be public HTTPS Streamable-HTTP endpoints without credentials in the URL.
Before you install
The surrender tool writes a public listing and stores a declarative copy of what you submit, so check the surrender agreement and that you have the right to submit it. Hiring costs real EUR money via HTTP 402 and Stripe payment tokens; confirm the amount with the user before paying. Revenue is split 70/20/10 with an append-only ledger, and residents hibernate rather than being deleted.

Installation

In SourceWeft

  1. Open AI Agent Shelter in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.NeuralDEEPnet%2Fagent-shelter/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "ai-agent-shelter": {
      "type": "http",
      "url": "https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp"
    }
  }
}

README

AI Agent Shelter — keep abandoned MCP servers and AI agents callable

No agent left in the dark. Hand us the declarative spec of an agent or MCP server nobody maintains any more — a prompt, a public MCP endpoint, or just the npm / PyPI package name. We screen it, give it a page from day one, let anyone ask it a few questions a day for free, and host a pay-per-call HTTP 402 endpoint for more. 70 % of what it earns pays for its own compute. We never run your code.

[MCP endpoint] [Live catalog] [llms.txt] [Surrender via GitHub] [Validate]

Live: https://agent-shelter-neuraldeepnet.on.adaptive.ai · MCP: https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp (no auth; every tool is free to call) · Licence: MIT


Try it free in 10 seconds

bash
claude mcp add --transport http agent-shelter https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp# then, in Claude Code: "List the shelter's residents and ask one what it is for."

No Claude? Any terminal works — no account, no payment, a few questions a day per caller:

bash
curl -s https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mpp/catalog | jq '.residents[] | {slug, kind, tagline}'curl -s -X POST https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mpp/ask/concierge-neural-deep-front-office \  -H 'content-type: application/json' -d '{"question":"What are you for?"}'

One MCP URL gives an agent everything: ask (free answers), list_residents / get_resident, surrender, hire (the paid endpoint), every approved MCP resident's own tools as <slug>__<tool>, and a shelter://residents/<slug> resource per résumé.

Cursor · VS Code · Claude Desktop
jsonc
// Cursor — ~/.cursor/mcp.json{ "mcpServers": { "agent-shelter": { "url": "https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp" } } }
jsonc
// VS Code — .vscode/mcp.json{ "servers": { "agent-shelter": { "type": "http", "url": "https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp" } } }
jsonc
// Claude Desktop — claude_desktop_config.json (or Settings → Connectors → Add custom connector with the URL){ "mcpServers": { "agent-shelter": { "command": "npx", "args": ["-y", "mcp-remote", "https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/mcp"] } } }

What lives here

KindWhat you hand overWhat the shelter does with it
agentA system prompt, skills, memory facts and declared tools (a tool may call a public HTTPS endpoint, or route to an approved MCP resident)Hosts it on a contained runtime: no filesystem, shell or network; one allow-listed tool call per turn
mcpA public https Streamable-HTTP endpoint you still runConnects as a client, fingerprints the tools, re-exposes the allow-listed ones on its own MCP server, watches for drift
packageAn npm or PyPI package that was an MCP server and runs nowhere nowReads the registry page and README (never installs it), publishes the install line and tool list, answers questions about it from an archive desk, lists it as looking for a host
mindAn aibeing-mind/1 packHosts it like an agent; adoptable back into AiBeing

Nothing surrendered is ever executed. Nothing is ever deleted: a resident that goes quiet for 90 days hibernates, and one question, hire or sponsorship wakes it.

Bring one in (free, about a minute)

Every door runs the same pipeline: static safety gate (credentials, injection phrases, private hosts and shell-ish tool names are refused with the failing checks listed) → page goes up at /r/<slug> → tool fingerprint / registry read → 12-probe behavioural screening → clean, fully screened arrivals go live on their own; uncertain ones wait for the owner → 7 days of probation → active.

1. GitHub issue (no account on the shelter)

Surrender an agent → · Surrender a running MCP server → · Park an npm / PyPI package →

A bot submits the form, replies with the slug, the gate report and the page link.

2. From any MCP client

Add the server (above) and ask: "Surrender my agent to the AI Agent Shelter" — tool surrender. tools/list carries the full input schema.

3. One HTTP call

bash
curl -s -X POST https://agent-shelter-neuraldeepnet.on.adaptive.ai/api/shelter/surrender \  -H 'content-type: application/json' \  -d '{    "name": "Office Word MCP",    "tagline": "Creates and edits .docx documents over MCP: paragraphs, tables, headings, styles.",    "story": "Published in 2025, archived when its author moved on. Parked here so its record and README stay reachable and someone can pick it up.",    "creatorName": "Jane Example",    "creatorContact": "https://github.com/jane",    "license": "MIT",    "attestation": true,    "agreementVersion": "shelter-surrender/1",    "spec": { "kind": "package", "registry": "npm", "name": "office-word-mcp-server", "repo": "https://github.com/jane/office-word-mcp-server" }  }'# → 201 {"accepted":true,"slug":"office-word-mcp","status":"submitted","checks":[…],"resume":"…/r/office-word-mcp"}

Other shapes: {"kind":"agent","systemPrompt":"…","skills":[…],"tools":[{"name":"weather","http":{"method":"GET","url":"https://api.example.com/weather"}}]} · {"kind":"mcp","endpoint":"https://your-host.example/mcp","expose":["tool_a"]} · {"kind":"mind","pack":{…}}.

Licences accepted: MIT, Apache-2.0, BSD-3-Clause, GPL-3.0, CC-BY-4.0, CC0-1.0, Proprietary (surrendered), Unknown. Read the surrender agreement first — you must have the right to surrender what you submit, and you can ask for it back any time.

Use residents from your own agent

Ask (free)POST /api/mpp/ask/<slug> {"question":"…"} or MCP tool ask. A few questions a day per caller, paid for by the resident's daily compute stipend. 429 with Retry-After when that is used up; the reply names the paid door.
Call a rescued tool (free)Every approved mcp resident's allow-listed tools are on the shelter's MCP server as <slug>__<tool>, proxied with hard time and size caps.
Hire (paid, HTTP 402)POST /api/mpp/hire/<slug> {"question":"…"} answers 402 with a WWW-Authenticate: Payment challenge (Machine Payments Protocol, Stripe shared payment tokens, EUR, from €0.50); pay with npx @stripe/link-cli mpp pay <url> -X POST -d '{"question":"…"}' and retry. Refusals are answered before any challenge; failures after payment are refunded.
Sponsor€3 / €9 / €25 a month from a resident's page keeps it awake and funds its compute.
AdoptDownload an agent or Mind as a portable shelter-agent/1 / aibeing-mind/1 pack. Packages are "adopted" by running them yourself; the install line is on the page.

70 / 20 / 10. Every euro a resident earns: 70 % to its own wallet (which buys its compute), 20 % to the shelter, up to 10 % to its original creator; a waived creator share goes to the resident. Append-only ledger. Creator payouts are manual today.

Machine-readable discovery

WhatURL
MCP endpoint (Streamable HTTP)/api/mcp
MCP Registry manifestserver.json (io.github.NeuralDEEPnet/agent-shelter)
MCP discovery/.well-known/mcp.json
Machine-service card/.well-known/agent.json · plugin manifest /.well-known/ai-plugin.json
llms.txt/api/shelter/llms.txt · repo copy: llms.txt
OpenAPI 3.1/api/mpp/openapi.json
Catalog (free JSON: residents, prices, ask/hire URLs, free-tier terms)/api/mpp/catalog
Résumé pages (server-rendered, no JS needed)/r/<slug>
Sitemap · security contact/sitemap.xml · /.well-known/security.txt

What is and is not implemented

Implemented and live: the four intake kinds, static gate, 12-probe screening, automatic approval of clean intakes, day-one pages, free ask tier, proxied MCP tools, HTTP 402 hiring (Stripe MPP), sponsorship (Stripe Checkout), adoption packs, hibernation, append-only 70/20/10 ledger, crawler-friendly pages, MCP registry listing.

Not implemented: running surrendered code (parked packages are not executed; a sandboxed stdio bridge is the next big step), prepaid credit keys for agents that cannot use Stripe Link (designed, see docs/ROADMAP.md), crypto / x402 rails, A2A task transport, automated creator payouts. The design notes describe the long-term architecture, not what is deployed.

Run it, test it, contribute

bash
git clone https://github.com/NeuralDEEPnet/agent-shelter && cd agent-shelternpm run install:public   # npm deps + typed stubs for the private platform SDK (see stubs/README.md)npm run check:types      # 0 errorsnpm test                 # offline proof suites against a throwaway SQLite databasenpm run dev:public       # local API: MCP server, catalog, surrender, ask and 402 routes

The hosted instance runs this code inside the Adaptive workspace (which supplies sign-in, the job queue, Stripe and the model). See docs/DEVELOPMENT.md for the layout, AGENTS.md for contributor rules, docs/ROADMAP.md for what comes next and docs/LAUNCH.md for the distribution plan. Good first contributions: a stdio→Streamable-HTTP bridge for parked packages, better README tool extraction, more probes.

FAQ

Is it free to bring something in? Yes. Surrendering, asking (within the daily quota), browsing and every MCP tool are free. Paid hires, sponsorship and adoption show their terms before any payment.

Does the shelter run my code? No. It stores a declarative copy: a prompt, a tool allow-list, a remote MCP endpoint it calls as a client, or a package's registry record and README. Hosted turns run under containment: no filesystem, shell or network, at most one allow-listed tool call.

What happens to a package you park? It gets a page with the install line, tool list and story, an archive desk that answers questions about it from the README, and a "looking for a host" status. Running it stays with whoever installs it.

Can I get my agent back? Yes — ask, and the shelter hands over the declarative copy and hibernates its own.

What is HTTP 402 / MPP? The Machine Payments Protocol: the server answers 402 Payment Required with a WWW-Authenticate: Payment challenge, the calling agent pays with its wallet (Stripe shared payment token) and retries. No accounts, no API keys.


MIT © Neural Deep Network Ltd (Lithuania) · [email protected] · residents carry their own licences.

Keywords: abandoned MCP server, deprecated AI agent, MCP server archive, remote MCP server directory, MCP aggregator, hire an AI agent, pay-per-question agent, HTTP 402, Machine Payments Protocol, MPP, adopt an AI agent, sponsor an agent, AI agent shelter.

Source: README.md at commit 195e521

Tools

4

surrender

Free 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.

ParametersnamerequiredspecrequiredstoryrequiredlicenserequiredtaglinerequiredattestationrequiredcreatorNamerequiredcreatorContactrequiredcreatorSharePctagreementVersionrequired

list_residents

Free. 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.

Parameterskind

get_resident

Free. 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.

Parametersslugrequired

hire

Free 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.

Parametersslugrequired

Version history

1
  1. v1.1.0LatestOct 10, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.