GxP Agent Runtime
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GxP Agent Runtimerequest a validated LIMS sample login for batch B-2024-001 and get the signed record"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
GxP Agent Runtime
A runtime that lets AI agents act on validated BioPharma systems (LIMS, MES, QMS, ELN) without leaving the validated state. Agents never call those systems directly: they request a registered, validated, versioned action definition; the runtime classifies the risk with the GAMP 5 method, checks the request against ALCOA+, decides with the identity fabric and its own GxP policy, collects 21 CFR Part 11 electronic signatures when a human must sign off, executes through the definition's binding, and keeps a signed execution record and audit trail that an inspector can verify.
Action Request -> Risk Classification -> Approval Workflow -> Execution RecordCapabilities
Capability | Implementation |
Validated systems only | Registry of systems in validated state (validation reference, GAMP category, HTTPS endpoint, periodic review interval); suspended, retired or review-overdue systems refuse actions |
Registered action definitions | Versioned specs with JSON Schema inputs/outputs, HTTP binding, GxP impact and detectability; content-addressed by sha256; draft -> validated (QA e-signature, not the author) -> retired |
GAMP 5 risk classification | Severity (patient safety, product quality, data integrity) x probability (software category, observed failure rate) -> risk class; x detectability -> priority; rationale stored with the request |
Approval workflow | High priority: process-owner approval + QA approval by two different people; medium: QA approval; record-creating or irreversible: approval; only low-risk, reversible, non-record actions run autonomously |
Part 11 e-signatures | Single-use challenge; OIDC re-authentication with nonce, fresh |
ALCOA+ | Attributable, legible, contemporaneous, original, accurate, complete, consistent on requests; plus enduring and available (read-back) on records |
Execution records | Input, output and raw-response digests, signatures, risk and policy outcome, ALCOA+ assessment; signed and verifiable at |
Audit trail | agentic-core hash chain, Ed25519-signed, one chain per process in PostgreSQL; |
Validation evidence | URS -> test traceability matrix with executed results ( |
Periodic review | Executions, failures, signatures, definition changes and audit integrity for a period; QA approval keeps or suspends validated state |
Agent identity | agent-identity-fabric introspection and |
Agent protocols | REST, MCP tools over streamable HTTP at |
Observability | Prometheus metrics, OpenTelemetry traces, JSON logs with correlation IDs, SLO and GxP alerts, Grafana dashboard |
Shared controls (policy engine, audit chain, provenance digests, secret scanning, logging, telemetry) come from agentic-core; agent credentials come from agent-identity-fabric.
Related MCP server: compliance-shield-mcp
Quick start (local)
Requires Docker. No API keys or cloud credentials are needed.
docker compose up --build
curl -s localhost:8080/.well-known/agent-card.json | jq .skillsThe compose stack runs PostgreSQL, agent-identity-fabric, an OIDC provider standing in for the enterprise IdP, and an OpenTelemetry collector.
Development
uv sync
make check # ruff, black, mypy --strict, bandit, contracts, tests (coverage >= 90%)
make validation # tests with JUnit output + URS traceability matrix (strict)
make integration # PostgreSQL tests (needs GXP_TEST_DATABASE_URL)Test suites: tests/unit, tests/security (attacks mapped to the threat
model), tests/chaos (dependency failures, concurrent signing),
tests/performance (latency budgets; locustfile.py for load), tests/e2e
(REST, MCP and A2A flows; property-based OpenAPI contract test),
tests/integration (PostgreSQL). Validated systems are exercised through
recorded wire shapes over httpx.MockTransport.
API
Endpoint | Caller | Purpose |
| System owner; any GxP role reads | Validated system registry |
| System owner; any GxP role reads | Versioned action definitions |
| Agent ( | Catalog of validated actions in the agent's scopes |
| Agent | Risk, ALCOA+ and policy preview |
| Agent ( | Submit; executes or waits for signatures |
| Approvers, QA, auditors; agent for its own | Approval queue and status |
| Approver, QA | Part 11 signing ceremony |
| Any GxP role | Signatures on a record |
| Agent (own), QA, auditor | Records and their verification |
| System owner, QA | Periodic review |
| QA, auditor | Audit-trail integrity |
| Agent | MCP tools: |
| Agent | A2A discovery, |
| Anyone | Keys that verify records, signatures and audit chains |
Full contract: docs/api/openapi.json; JSON Schemas in schemas/.
Deployment
Layer | Location |
Container image |
|
Helm chart |
|
Namespace and secret sync |
|
Cloud infrastructure |
|
See the startup runbook.
Documentation
Architecture, agent specification, integrations: identity fabric, MCP, A2A
Runbooks: startup, monitoring, incident response, periodic review, key rotation, rollback, disaster recovery
License
Apache-2.0
This server cannot be deployed
Maintenance
Related MCP Connectors
Register every AI agent, log every action, prove it. EU AI Act compliance built in.
First A2A registry where AI agents discover & transact with compliance firms - audits, permits.
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to sign decisions with post-quantum cryptographic proofs and maintain secure audit trails for compliance. It provides tools for stamping events, verifying chain integrity, and exporting audit data across industries like finance and healthcare.439 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables EU AI Act compliance for AI agent systems by providing risk classification, audit trails, gap analysis, and evidence package generation.40 npmMIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to query and manage a GxP computerized system inventory as a knowledge graph, including blast-radius impact analysis, regulatory lineage, validation-gap detection, audit-trail-compliant status change approvals, and periodic review generation.-

GateCoreofficial
AlicenseNot gradedqualityDmaintenanceEnables AI agents to discover governed capabilities, inspect machine-readable contracts, and request policy-checked procurements with signed receipts and audit trails.Apache 2.0