
Zentric Protocol Mcp
io.github.ZentricProtocolPublished by GitHub account ZentricProtocolv0.1.3Updated Oct 28, 2026
Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.
Overview
Local MCP server that sends text to Zentric Protocol's hosted API to detect prompt injection and PII, returning a verdict and signed audit report.
- What you can do
- Analyze text for prompt injection and jailbreak signatures, returning a CLEARED or BLOCKED verdict with matched signatures and a risk score.
- Detect and anonymize PII such as emails, phone numbers, national IDs, IBAN and SWIFT codes, with redact, mask, tokenize or pseudonymize operators.
- Return a signed audit record per request with UUID, SHA-256 hash, UTC timestamp and latency, intended as compliance evidence.
- Check inputs at several points in an agent pipeline, such as user messages, tool output, RAG chunks and memory reads.
- When to use it
- Useful when an assistant or agent pipeline ingests untrusted text and you want a deterministic pre-check plus an auditable record before content reaches the model. Suited to teams with compliance or audit needs around prompt injection and personal data.
- Requirements
- Runs locally via npx from the npm package zentric-protocol-mcp, so Node.js is needed. Requires a Zentric Protocol API key supplied through the ZENTRIC_API_KEY environment variable; the free tier is 10,000 requests per month. Network access to the Zentric Protocol API is required.
Installation
In SourceWeft
- Open Zentric Protocol Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
ZENTRIC PROTOCOL
Prompt injection detection & PII anonymization with a signed audit trail — for LLM apps and AI agents.
[Status] [Latency] [Precision] [GDPR] [EU AI Act] [CCPA]
Every prompt, RAG chunk and tool output inspected before it reaches your model — deterministic CLEARED / ANONYMIZED / BLOCKED verdicts with a signed audit record (SHA-256 + UUID + UTC) per request.
Detection tells you what happened. The audit record is what you show your auditor — GDPR Art. 30 evidence today, EU AI Act readiness tomorrow.
→ Get API key (free, 10,000 req/mo) · Quickstart · Integrity Report v1.0 (PDF)
[Zentric Protocol — See it in action]
A real prompt injection attempt. Caught in <0.1ms. Your model never sees it.
Repository Scope & Commercial License
This repository exists for transparency and contribution — not as a deployable alternative to the hosted service.
Cloning this repository does not give you access to the Zentric processing service. The detection engine that inspects prompts, detects PII, and generates signed audit reports runs on Zentric's infrastructure and requires an active license.
Why publish the middleware?
Because trust is infrastructure. You should be able to verify how authentication works, how your API key is validated, and how subscription state is checked before your requests reach the engine. We believe in auditability at every layer — including our own enforcement code.
Contributions welcome
We accept contributions to the middleware, webhook handler, and Supabase schema. Open a PR or file an issue. For security-related contributions, see the Security section.
Getting access
What is Zentric Protocol?
Zentric Protocol is an infrastructure integrity layer for AI systems. It sits between your application and your LLM, examining every signal — prompts, responses, user inputs — and returning a cryptographically-signed verdict before execution continues.
It is not a filter. It does not guess. It applies deterministic rules across a standardized pipeline and returns a structured, auditable JSON report for every request.
Performance
Zentric uses deterministic signature matching — not an ML classifier. Every block is a known pattern match, which means 100% precision on known patterns and zero false positives: nothing is ever blocked unless it matches a catalogued signature. Verdicts are returned in sub-millisecond time (no model in the hot path), so the same input always produces the same verdict.
Any published metric is reproducible: run npm run benchmark (benchmarks/run.mjs) against the public deepset/prompt-injections dataset to verify the numbers yourself.
The Three Modules
01 · IntegrityGuard
Detects prompt injection, jailbreak attempts, and instruction overrides before they reach your LLM.
- 22 catalogued injection signatures
- 7 supported languages (EN, ES, FR, DE, PT, ZH, JA)
- Deterministic multilingual signature matching — no ML model in the verdict path
- Mean server-side processing: <0.1ms (sub-millisecond; no model in the hot path)
02 · PrivacyGuard
Identifies and anonymizes PII in prompts and responses. Regional standards treated as first-class entities.
- 12 PII entity types, format-validated (Luhn, IBAN mod-97, mod-11, NIF/NIE checksum): SSN, NIF, CPF, CURP, IBAN, SWIFT, passport, email, phone, and more
- Regional pattern recognition (EU, US, LATAM)
- Anonymization operators: redact, mask, tokenize, pseudonymize
03 · ZentricReport
Every request that passes through the protocol generates a signed, immutable audit record.
API Reference
Authentication
Response
Verdict States
SDKs
Compliance Coverage
Zentric Protocol is designed from the ground up for regulated AI deployments.
Pricing
→ See plans · → Get API key · → Contact for Enterprise
Architecture Principles
Deterministic. The same input always produces the same verdict. No probabilistic black boxes in the critical path.
Stateless. The protocol does not store your data. Each request is processed and returned. The audit record is yours.
Composable. Deploy the full stack, a single guard, or wire only the audit layer into existing infrastructure.
Auditable. Every verdict is signed with SHA-256, timestamped in UTC, and assigned a UUID. Your compliance team will thank you.
For Agent Pipelines
Agent attacks don't arrive through the chat input. They arrive through tool call responses, RAG chunks, and memory retrievals — any external content that enters the prompt window. Your system prompt doesn't protect you here: it doesn't run until after the input is already parsed.
Wire Zentric at every ingestion point, not just on user messages:
- LLM input — user messages before they reach the model
- Tool output — external API responses before they re-enter the context window
- RAG retrieval — document chunks before they are assembled into the prompt
- Memory reads — stored context before it is injected into the next turn
One POST to /v1/analyze. The verdict comes back in sub-millisecond time. The agent continues or halts based on the result. Nothing else changes in your pipeline.
MCP Server — Claude Desktop Integration
Zentric Protocol ships a native Model Context Protocol (MCP) server that integrates directly with Claude Desktop and any MCP-compatible agent runtime.
What it does
The MCP server exposes Zentric's detection engine as a native MCP tool. When wired into Claude Desktop, the agent automatically calls analyze_prompt before sending any input to the LLM — user messages, tool responses, RAG chunks, and memory retrievals are all checked.
MCP Tool exposed
Returns: verdict (CLEARED / BLOCKED), risk_score, matched signatures, pii_entities, report_hash (SHA-256), latency_ms.
Install via npm
Claude Desktop configuration
Add to your claude_desktop_config.json:
Get your API key at zentricprotocol.com/quickstart — free tier is 10,000 requests/month, no credit card required.
MCP server source
The MCP server source code is in /mcp-server. It is built with the Model Context Protocol SDK and published to npm as zentric-protocol-mcp.
Security
We take the security of this protocol seriously. If you discover a vulnerability, please report it responsibly.
- Email: [email protected]
- Subject:
[SECURITY] <brief description> - Response SLA: 48 hours acknowledgement, 7 days resolution target
We do not operate a public bug bounty program at this time. Responsible disclosure is acknowledged in our changelog.
Roadmap
- IntegrityGuard v1.0 — 22 signatures, 7 languages
- PrivacyGuard v1.0 — 12 PII types, EU/US/LATAM
- ZentricReport v1.0 — SHA-256, UUID, GDPR Art.30
- REST API (production)
- Python SDK — Q3 2026
- Node.js SDK — Q3 2026
- Streaming support (SSE) — Q3 2026
- Webhook callbacks — Q4 2026
- Self-hosted deployment option — 2027
Contact
Zentric Protocol · Infrastructure Integrity for the AI Era
zentricprotocol.com · © ZP MMXXVI · v1.0.0
Built for CTOs who know that trust is infrastructure, not a feature.
Source: README.md at commit 6f83c07
Tools
0Version history
1- v0.1.3LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.