mcp-context-receipts
Privacy-first, tamper-evident receipts for MCP tool calls. It hashes and signs arguments/results so you can verify what ran, when, without storing raw payloads.
README
MCP Context Receipts
Privacy-first, tamper-evident receipts for Model Context Protocol tool calls.
MCP makes it easy to give models tools. The missing piece is a small, portable answer to: what exactly ran, when, and can I prove the record was not edited?
This project provides a dependency-free Node.js MCP server over stdio with two tools:
create_receipt— hashes the tool arguments and result, then returns a signed receipt.verify_receipt— verifies the receipt's hash chain and HMAC signature.
Raw arguments and results are never persisted. The server emits only a compact receipt, so it can be piped into logs, an audit store, or a test harness.
Quick start
Requires Node.js 20+.
npm start
Add it to an MCP client that supports stdio servers:
{
"mcpServers": {
"context-receipts": {
"command": "node",
"args": ["/absolute/path/to/mcp-context-receipts/src/server.js"],
"env": { "MCP_RECEIPT_SECRET": "replace-in-your-environment" }
}
}
}
Receipt format
Each receipt includes a monotonically increasing sequence number, UTC timestamp, server and tool identity, SHA-256 hashes of the input and output, elapsed time, the previous receipt hash, and an HMAC-SHA256 signature. The chain makes deletion or reordering detectable when receipts are stored externally.
Set MCP_RECEIPT_SECRET in the environment for production use. A development fallback is used only to make local exploration easy; the server prints a warning to stderr.
Development
npm test
The core receipt functions are deliberately separate from the MCP transport so they can be embedded in another MCP server or tested without a running client.
Status
Early, intentionally small, and useful as a building block. Contributions that add durable sinks, key rotation, or OpenTelemetry export should preserve the default no-raw-payload behavior.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.