Allows AI agents to issue signed receipts that verify actions taken and disclose any commercial influences or conflicts of interest.
Also known as getstub/recipes, recipes, @getstub/mcp-check
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- 244
- Latest version
- 0.1.0
- Last commit
- Sep 20, 2026
- License
- MIT
What is Stub MCP?
Stub allows AI agents to issue signed receipts that verify actions taken and disclose any commercial influences or conflicts of interest.
Summary generated from the project's README
About Stub MCP server
Issuing signed receipts to verify agent actions and disclose commercial influences is what check enables for developers building autonomous agents. This server allows an agent to generate a small, signed record that details who requested an action, what was performed, any money that moved, and whether commercial conflicts like commissions or paid placements influenced the outcome. These records are stored in a neutral registry where users can verify them independently of the agent's own servers.
Developers can integrate this functionality using JavaScript or Python via the @getstub/agent or getstub packages. The system requires an operator ID to identify the agent, and the first run generates a keypair saved locally to .stub-keys.json. While the service includes a free tier of 1,000 stubs per month, it requires a live connection to the registry to issue any records. It is designed to be implemented directly within the ranking logic of an agent, ensuring that disclosures are automatically captured at the moment a decision is made.
What you can do with it
- 1Verify agent decisionsA user can check a neutral registry to confirm exactly what an agent did and what commercial influences were present during a transaction.
- 2Prove absence of conflictsAn agent can issue a signed statement proving that no commercial interests influenced a specific recommendation.
Written from the project's README. Every use case is checked against a quote from it.
How to install Stub MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Stub MCP in Claude Code
$ claude mcp add recipes -- npx -y @getstub/mcp-checkInstall Stub MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"recipes": {
"command": "npx",
"args": [
"-y",
"@getstub/mcp-check"
]
}
}
}Install Stub MCP in VS Code
.vscode/mcp.json
{
"servers": {
"recipes": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@getstub/mcp-check"
]
}
}
}Install Stub MCP in VS Code CLI
$ code --add-mcp '{"name":"recipes","type":"stdio","command":"npx","args":["-y","@getstub/mcp-check"]}'Install Stub MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"recipes": {
"command": "npx",
"args": [
"-y",
"@getstub/mcp-check"
]
}
}
}Install Stub MCP in Codex
$ codex mcp add recipes -- npx -y @getstub/mcp-checkInstall Stub MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.recipes] command = "npx" args = ["-y", "@getstub/mcp-check"]
Install Stub MCP in Gemini CLI
$ gemini mcp add -s user recipes npx -- -y @getstub/mcp-checkInstall Stub MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"recipes": {
"command": "npx",
"args": [
"-y",
"@getstub/mcp-check"
]
}
}
}Configuration
STUB_OPERATOR_IDSTUB_REGISTRYRegistry host to resolve receipts against. Defaults to https://api.getstub.dev
| Name | Description | |
|---|---|---|
| STUB_OPERATOR_ID | — | |
| STUB_REGISTRY | Registry host to resolve receipts against. Defaults to https://api.getstub.dev |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablegetstub/recipes is public and reachablegithub.com/getstub/recipes ↗Pass
- Package names this repository as its source@getstub/mcp-check names getstub/recipes as sourcenpmjs.com/package/@getstub/mcp-check ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-20github.com/getstub/recipes ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @getstub/mcp-checkPass
- No critical advisory in the package or its dependencies99 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubStub recipes
Working reference integrations for Stub, the allegiance receipt registry for AI agents.
Each recipe is a runnable agent with Stub wired in at the line where the ranking picks a winner. Clone one, run it, read the receipt it produces.
Every recipe here is a reference and a simulation. No real merchants, no real money, no real users. Nobody is running these in production, and each README says so. The point is to show exactly where a receipt belongs in code you recognise.
The recipes
| Recipe | What it shows | Language |
|---|---|---|
tool-loop |
The primitive every framework wraps. A model, two tools, a loop. | JavaScript |
acp-commerce |
Allegiance lives upstream of checkout, in the ranking. | JavaScript |
mcp |
A public check server any agent can add, plus the operator issuing pattern. | JavaScript |
langchain-python |
The same integration inside a LangChain agent. | Python |
vercel-ai-sdk |
The biggest agent surface in JavaScript. | JavaScript |
insurance-advice |
The primitive outside commerce, with real stakes. | Python |
Every recipe runs against the live registry and issues real receipts, under an operator id you choose. The free tier is 1,000 stubs a month, so trying all six costs nothing. There is no offline mode and no mock registry: the only way to issue a stub is to issue one.
The badge above
These recipes are exercised against the live registry every day, and the badge is drawn from the receipts that run produces. It is not a build status: it says the reference agents ranked their catalogues, disclosed what influenced the result, and issued signed records anyone can open. Click it to read them.
If it ever goes quiet, the recipes stopped working and this repo is telling you so before you clone it.
Start here
If you are new to this, read tool-loop first. It is the smallest one and it carries the lesson the others repeat: the model does nothing wrong, the ranking decided.
cd tool-loop
npm install
export STUB_OPERATOR_ID=op_yourname_toolloop
npm run demo
Pick an operator id that is yours. The first run registers it and saves your
keypair to .stub-keys.json, which is gitignored. Every run after that uses the
same identity.
The demo prints the ranking your code produced, with the reason beside each item, and then a receipt link anyone can open.
When you are ready to deploy
The recipes generate a fresh keypair each run, which is right for reading and wrong for production. PRODUCTION.md covers what changes: persisting your identity, where the receipt belongs, what never goes in the free text, and the mistakes we made taking our own agent live.
What a stub is
When your agent acts for someone, it issues a small signed record: who asked, what was done, what money moved, and what commercial influence applied. The person served checks it at a neutral registry, not on your servers and not on ours.
Here is a live one before you install anything:
https://api.getstub.dev/check/72b4baee1719ec34acc5df5c514a12fd2e19b9a6776de4b45706988f765c77d8
The integration, in full
import { Stub, influenced } from '@getstub/agent';
const stub = new Stub({
operator: 'Your Agent',
declared: {
paid_by: 'the user, subscription',
conflicts: ['commission'],
},
});
// at the line where your ranker picks a winner:
const inf = [];
if (pick.paid_placement) inf.push(influenced.placement(pick.seller));
if (pick.commission_pct) inf.push(influenced.commission(pick.commission_pct + '%'));
const receipt = await stub.issue({
principal: user.id, // hashed on your side, never sent raw
agent: 'your-agent',
requested: query,
done: `booked ${pick.name}`,
value_moved: { amount: pick.price, currency: 'USD' },
not_disclosed: inf, // an empty array is signed proof none applied
});
Python is the same shape:
from getstub import Stub, influenced
Two things that keep coming up
Nobody hand writes disclosures. Your ranking code already knows when a commission or a placement fee shaped a result, because it applied it. The receipt reads the same flags at the same line. It scales the way your ranking scales.
An empty disclosure is not nothing. It is a signature saying conflicts exist in your business and none of them touched this action. That is worth more than silence, and it is why honest operators have something to gain here.
Install
npm install @getstub/agent
pip install getstub
Both clients sign over the same canonical form, verified rather than assumed: the Python test suite signs a stub and has the registry code verify it.
Free tier
1,000 stubs a month. Checking is free forever, because charging the person being served to verify would defeat the point.
Links
- getstub.dev
- Registry: https://api.getstub.dev
- Witness key: https://api.getstub.dev/witness
- Directory of operators: https://api.getstub.dev/directory
Copyright Stub 2026
Stub MCP questions
How do I add Stub MCP to Claude Code?
Run claude mcp add recipes -- npx -y @getstub/mcp-check in your terminal. Add --scope user to make it available in every project.
How do I add Stub MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Can I use this in production?
The provided recipes generate fresh keypairs each run which is unsuitable for production; you must follow specific steps to persist your identity for live deployment.
What information is included in a stub?
A stub is a signed record containing who requested the action, what was performed, the value moved, and any commercial influences applied.