Records and seals AI agent payments as signed records on your local machine to ensure auditability and intent verification.
Also known as luca-network/spr, spr, @luca-network/spr-mcp, @luca-network/spr-sdk
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.2.0
- Last commit
- Nov 12, 2026
- License
- Apache-2.0
What is SPR MCP?
SPR records and seals AI agent payments as signed records on your local machine to ensure auditability and intent verification.
Summary generated from the project's README
About SPR MCP server
SPR provides a way to record and seal AI agent payments as signed records on a local machine. This tool is designed for developers and finance teams who need to ensure auditability and verify the intent behind every transaction an agent makes. By running the MCP server locally, users can create a verifiable history of what an agent declared it would pay versus what was actually settled.
To use the server, you must configure environment variables including SPR_AGENT_ID, SPR_ENTITY, and a directory path for the records. It integrates with clients like Claude Desktop, Cursor, and Claude Code via npx. Developers using the OpenAI Agents SDK or LangChain can also connect through the provided JavaScript SDK. The system uses specific tools such as record_intent to declare a purpose before payment, check_payment to verify the transaction stays within declared limits, and record_settlement to finalize the entry after the payment occurs.
What you can do with it
- 1Verify payment intentAn AI agent can declare its purpose and spending limits before executing a transaction to ensure auditability.
- 2Audit local payment recordsA developer can use the verification tools to check that the sealed records in a folder are consistent with the company's public key.
- 3Manage merchant disputesA merchant can export a package of evidence to respond to a chargeback by showing the buyer's sealed intent and authentication.
- 4Integrate with agent frameworksDevelopers can connect the server to various Python-based agent frameworks like CrewAI or the Microsoft Agent Framework.
Written from the project's README. Every use case is checked against a quote from it.
How to install SPR MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall SPR MCP in Claude Code
$ claude mcp add --env 'SPR_AGENT_ID=<SPR_AGENT_ID>' --env 'SPR_ENTITY=<SPR_ENTITY>' spr -- npx -y @luca-network/spr-mcpInstall SPR MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"spr": {
"command": "npx",
"args": [
"-y",
"@luca-network/spr-mcp"
],
"env": {
"SPR_AGENT_ID": "<SPR_AGENT_ID>",
"SPR_ENTITY": "<SPR_ENTITY>"
}
}
}
}Install SPR MCP in VS Code
.vscode/mcp.json
{
"servers": {
"spr": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@luca-network/spr-mcp"
],
"env": {
"SPR_AGENT_ID": "<SPR_AGENT_ID>",
"SPR_ENTITY": "<SPR_ENTITY>"
}
}
}
}Install SPR MCP in VS Code CLI
$ code --add-mcp '{"name":"spr","type":"stdio","command":"npx","args":["-y","@luca-network/spr-mcp"],"env":{"SPR_AGENT_ID":"<SPR_AGENT_ID>","SPR_ENTITY":"<SPR_ENTITY>"}}'Install SPR MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"spr": {
"command": "npx",
"args": [
"-y",
"@luca-network/spr-mcp"
],
"env": {
"SPR_AGENT_ID": "<SPR_AGENT_ID>",
"SPR_ENTITY": "<SPR_ENTITY>"
}
}
}
}Install SPR MCP in Codex
$ codex mcp add spr --env 'SPR_AGENT_ID=<SPR_AGENT_ID>' --env 'SPR_ENTITY=<SPR_ENTITY>' -- npx -y @luca-network/spr-mcpInstall SPR MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.spr] command = "npx" args = ["-y", "@luca-network/spr-mcp"] [mcp_servers.spr.env] SPR_AGENT_ID = "<SPR_AGENT_ID>" SPR_ENTITY = "<SPR_ENTITY>"
Install SPR MCP in Gemini CLI
$ gemini mcp add -s user -e 'SPR_AGENT_ID=<SPR_AGENT_ID>' -e 'SPR_ENTITY=<SPR_ENTITY>' spr npx -- -y @luca-network/spr-mcpInstall SPR MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"spr": {
"command": "npx",
"args": [
"-y",
"@luca-network/spr-mcp"
],
"env": {
"SPR_AGENT_ID": "<SPR_AGENT_ID>",
"SPR_ENTITY": "<SPR_ENTITY>"
}
}
}
}Configuration
SPR_AGENT_IDRequiredThe agent's ID, such as agt_research
SPR_ENTITYRequiredThe company the agent pays for
SPR_BINDINGon, to return the nonce to sign with each x402 intent
SPR_DIRThe book's folder (default ./spr-books); it holds the company's private key
SPR_TIME_ZONEThe company's time zone for accounting dates (default UTC)
| Name | Description | |
|---|---|---|
| SPR_AGENT_ID | The agent's ID, such as agt_research | Required |
| SPR_ENTITY | The company the agent pays for | Required |
| SPR_BINDING | on, to return the nonce to sign with each x402 intent | |
| SPR_DIR | The book's folder (default ./spr-books); it holds the company's private key | |
| SPR_TIME_ZONE | The company's time zone for accounting dates (default UTC) |
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 reachableluca-network/spr is public and reachablegithub.com/luca-network/spr ↗Pass
- Package names this repository as its source@luca-network/spr-mcp, @luca-network/spr-sdk name luca-network/spr as sourcenpmjs.com/package/@luca-network/spr-mcp ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for @luca-network/spr-mcp, @luca-network/spr-sdknpmjs.com/package/@luca-network/spr-mcp/v/0.2.0#provenance ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/luca-network/spr ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @luca-network/spr-mcp, @luca-network/spr-sdkPass
- No critical advisory in the package or its dependencies101 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 GitHubSPR: the Sealed Payment Record
Your AI agent pays for data, compute and services, and your finance team and auditor can't see what each payment was for. SPR records every payment your agent makes, before and after it pays, sealed with your company's own key on your own machine. Anyone can check the seals. No service has to be trusted, Luca's included.
npx -y @luca-network/spr-mcp
Free and open: Apache-2.0, with a royalty-free patent commitment (PATENTS.md).
Use it from your AI tool
Every setup below runs the same MCP server on your machine. Set SPR_AGENT_ID (your agent) and SPR_ENTITY (the company it pays for); records go to SPR_DIR.
Claude Desktop: add to claude_desktop_config.json:
{ "mcpServers": { "spr": { "command": "npx", "args": ["-y", "@luca-network/spr-mcp"],
"env": { "SPR_AGENT_ID": "agt_research", "SPR_ENTITY": "Example Co", "SPR_DIR": "/Users/you/spr-books" } } } }
Cursor: the same block in .cursor/mcp.json.
Claude Code:
claude mcp add spr -e SPR_AGENT_ID=agt_research -e SPR_ENTITY="Example Co" -- npx -y @luca-network/spr-mcp
OpenAI Agents SDK and LangChain (JavaScript):
import { SprBook, toOpenAIAgentsTools, toLangChainTools } from "@luca-network/spr-sdk";
const book = new SprBook({ dir: "./books", agentId: "agt_research", entity: "Example Co" });
const tools = toOpenAIAgentsTools(book, tool); // tool from "@openai/agents"; or toLangChainTools(book, tool)
CrewAI, Microsoft Agent Framework, Google ADK and the Claude Agent SDK (Python): each connects to the MCP server in a few lines. See examples/.
Any other MCP client: run npx -y @luca-network/spr-mcp over stdio with the two settings above.
The agent then calls record_intent before it pays, check_payment to see whether the payment is inside what it declared, goes to the payee it named and wasn't paid already, and record_settlement after it pays. Each record is sealed in the book's folder.
A merchant's book works the same way for payments received: it can keep the buyer's own sealed intent, how the buyer authenticated, and the order and processor references, and export one payment's evidence for a chargeback response (export_dispute_pack).
A record shows:
- what the agent declared before it paid: the purpose, the most it could spend, and when the permission expired;
- what was actually paid, on which rail, to whom and when;
- whether the payment stayed inside what was declared;
- for x402 payments, whether the chain itself recorded which declaration the payment was made under. The payer signs a fingerprint of the sealed intent as the payment's nonce.
This repository holds:
| Path | What it is |
|---|---|
SPEC.md |
The format, draft 1 |
packages/spr |
@luca-network/spr, the reference library for JavaScript and TypeScript, with no dependencies, plus the test vectors and spr-verify |
packages/spr-sdk |
@luca-network/spr-sdk: seal your agents' payments locally, with withLuca(fetch) for x402 and tools for the OpenAI Agents SDK and LangChain |
packages/spr-mcp |
@luca-network/spr-mcp: the same calls as an MCP server, for Claude Desktop, Cursor or your own agent (npx @luca-network/spr-mcp) |
python |
spr-sdk for Python: the same format and the same books |
Seal an x402 payment in one line
import { SprBook } from "@luca-network/spr-sdk";
import { withLuca } from "@luca-network/spr-sdk/x402";
const book = new SprBook({ dir: "./books", agentId: "agt_research", entity: "Example Co" });
const pay = withLuca(book, { signer: account });
const res = await pay("https://data.example/prices", {
luca: { purpose: "Market data for the pricing model", max_amount_minor: 20000, currency: "USDC" },
});
res.luca.record; // sealed, matched to its intent, bound on chain
Check anything without Luca
npx spr-verify ./books-export --key company.pem # a package, and whose it is
python -m spr ./books-export --key company.pem
npx spr-verify --vectors # the library against the test vectors
python -m spr --vectors # the Python SDK against the same vectors
company.pem is the company's public key, obtained from the company and never from the package (book.publicKey() gives it). Without --key the checkers show only that a package is consistent with the keys it carries, and say so.
Security problems: see SECURITY.md.
An implementation in any language conforms when it gives the same answers as packages/spr/vectors/vectors.json.
Local SPR and hosted Luca
The packages here run on your own machine and make no call to Luca. Luca's hosted service is a separate product that a book can be sent to.
| Local SPR (these packages) | Hosted Luca | |
|---|---|---|
| Where it runs | Your machine, your folder, your key | Luca's service |
| What it records | The intent before paying and the payment after, as the agent reports them | The same, plus the payment as the rail itself reports it |
| Limits it checks | The declared intent: its cap, its expiry, whether it was withdrawn and the payee it named; the same invoice paid twice. Optionally the book's own mandate.json (limits, payees, a window for repeats), which whoever keeps the folder writes, so it is reported as authority: "self-declared" |
Mandates your finance team approves in Luca |
| Confirmation from the rail | None: the record is what the agent reported | The payment read from the rail, and any difference flagged |
| Accounting | None | Classification to your accounts (US GAAP, IFRS, tax), journal entries posted to your ERP, the month's close |
| Evidence | Seals anyone can check with spr-verify or python -m spr |
Evidence your auditor can check, and the month's audit package |
| Cost | Free, Apache-2.0 | A Luca account |
A book moves across with one call once finance has registered its key: book.sendToLuca(). Luca checks every seal before it stores anything.
Send the book to Luca (optional)
Finance registers the book's key with Luca once (book.registerWithLuca), and then book.sendToLuca() sends the book. Luca checks every seal before it stores anything, and sending the same book again changes nothing. Write to hello@luca.network for an account.
Changes
What changed in each version, and what you may need to change on upgrading: CHANGELOG.md.
Status
This is draft 1 of the format and version 0.1 of the libraries. We expect to change things as people use them. Tell us what breaks or what's missing: open an issue, or write to hello@luca.network.
License
Apache License 2.0 for the code: see LICENSE. Luca's patent commitment, which lets anyone implement the format with or without this code, is in PATENTS.md.
Luca (luca.network) uses SPR for its hosted accounting of agent payments. That covers reading the rails, classifying to US GAAP and IFRS, posting to the ERP, labels agreed with counterparties, and the close.
SPR MCP questions
How do I add SPR MCP to Claude Code?
Run claude mcp add --env 'SPR_AGENT_ID=<SPR_AGENT_ID>' --env 'SPR_ENTITY=<SPR_ENTITY>' spr -- npx -y @luca-network/spr-mcp in your terminal. Add --scope user to make it available in every project.
How do I add SPR MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Where are the payment records stored?
Records are stored locally on your own machine in a directory specified by the SPR_DIR environment variable.
Does the MCP server send data to Luca?
No, the local packages run on your machine and do not make any calls to Luca; Luca's hosted service is a separate product.
What information is included in a payment record?
A record includes the declared purpose, spending limits, expiration, actual amount paid, the payment rail, the recipient, and whether the payment matched the declaration.