ArtifactGuard
Enables AI agents to validate deliverables (JSON, ZIP, PDF, DOCX) against signed contracts, generating verifiable receipts with Ed25519 signatures.
README
ArtifactGuard: Signed AI Deliverable QA
Use ArtifactGuard as the last step before an AI agent delivers a JSON, ZIP,
PDF, or DOCX file to a customer. The buyer receives a deterministic
PASS, WARN, or FAIL receipt containing the artifact hash, contract hash,
individual checks, validator version, timestamp, and an Ed25519 signature.
One purchase case
An AI report agent creates result.json. Before delivery, it asks
ArtifactGuard to verify that the file is valid JSON, contains a status field
equal to ready, and does not contain configured forbidden patterns. The agent
then attaches the signed receipt to its final handoff.
This is delivery-contract QA, not antivirus scanning, legal certification, or a guarantee that the document's claims are true.
Buy through Apify
Set your own Apify API token locally. Never commit it.
export APIFY_TOKEN="your-token"
curl --fail-with-body \
-X POST \
"https://api.apify.com/v2/acts/analytical_gratefulness~artifactguard-agent/run-sync-get-dataset-items?format=json" \
-H "Authorization: Bearer ${APIFY_TOKEN}" \
-H "Content-Type: application/json" \
--data-binary @examples/validate_artifact.json \
--output receipt-response.json
validate-manifest costs USD 0.01 and validate-artifact costs USD 0.05.
Malformed requests and readiness checks do not trigger an application event
charge. A completed inspection whose result is FAIL is still a valid paid
result.
Buy directly with x402
The direct endpoint returns a standards-based 402 Payment Required response
with the price and payment requirements before any artifact is processed:
curl -i \
-X POST \
https://artifactguard-kl4hfo6j2q-as.a.run.app/v1/validate/artifact \
-H "Content-Type: application/json" \
--data-binary @examples/x402_validate_artifact.json
An x402-compatible buyer can satisfy that payment requirement and repeat the same request with a payment signature. Do not place wallet private keys in a request body, repository, or log.
Free discovery endpoints:
GET https://artifactguard-kl4hfo6j2q-as.a.run.app/capabilitiesGET https://artifactguard-kl4hfo6j2q-as.a.run.app/examplesGET https://artifactguard-kl4hfo6j2q-as.a.run.app/presets
MCP
The Apify Standby Actor exposes Streamable HTTP MCP at:
https://analytical-gratefulne--artifactguard.apify.actor/mcp
Supply your own Apify token as an Authorization: Bearer ... header in the MCP
client. Available tools include validate_manifest, validate_artifact, and
the free verify_receipt tool.
Verify a receipt independently
Install the single verifier dependency and pass either a receipt object or the full ArtifactGuard response envelope:
python -m pip install -r requirements.txt
python verify_receipt.py receipt-response.json
The verifier retrieves only the public Ed25519 key identified by the receipt, recomputes the canonical receipt hash, and verifies the signature. It never needs an API token, payment credential, or private key.
Files
examples/validate_artifact.json: Apify Actor input.examples/x402_validate_artifact.json: direct x402 API input.examples/validate_manifest.json: inexpensive manifest-only Actor input.verify_receipt.py: independent receipt hash and signature verifier.server.json: Official MCP Registry metadata for the authenticated remote.
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.