Sovereign MCP
Routes queries to local Ollama instances for AI model inference with automatic failover, enabling private and self-hosted operation.
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., "@Sovereign MCP Compute route: 'explain quantum computing'"
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.
Sovereign MCP
AI Infrastructure You Can Verify.
Every decision. Signed. Recorded. Provable.
Your Request
│
Sovereign Router
│
┌──────┼──────┐
│ │ │
Bedrock Groq Ollama
│ │ │
└──────┼──────┘
│
ERE Verification
(deterministic gate)
│
Ed25519 Sign
│
WORM Receipt
(append-only)
│
ResponseWhat It Does
Your AI provider can change pricing tomorrow, shut down your model, read every prompt, or refuse your workload. You have no recourse.
Sovereign MCP fixes this:
Provider independent — Swap from Claude to Llama to Ollama with zero code changes. If one goes down, the next catches it automatically.
Deterministically verified — Every output passes 5 verification gates before it ships. No stubs. No placeholders. No "TODO: implement."
Cryptographically signed — Ed25519 signature on every response. Prove what the AI said, when, and to whom.
Append-only audit trail — WORM-style receipts. Tamper-evident. Permanent. If it happened, you can prove it.
Self-hosted — Runs on your hardware, your network, your rules. No cloud dependency required.
Related MCP server: Predicate
Quick Start
# stdio mode (Claude Code / VSCode)
node sovereign-mcp.mjs
# HTTP mode (BobIDE / Android / any client)
node sovereign-mcp.mjs --httpConfigure providers in .env.local:
AWS_ACCESS_KEY_ID=your-key
AWS_SECRET_ACCESS_KEY=your-secret
AWS_REGION=us-east-1
BEDROCK_MODEL_ID=us.anthropic.claude-haiku-4-5-20251001-v1:0
GROQ_API_KEY=your-groq-key
OLLAMA_URL=http://localhost:11434Any provider you don't configure is skipped. The router uses what's available.
Tools
Tool | What it does |
| Route queries through the best available provider with automatic failover |
| Deterministic 5-pass verification — catches stubs, placeholders, secrets, broken code |
| WORM-seal any content with verification hash + Ed25519 signature |
| Route tasks to specialized agents or registered proxy services |
| Execute composable instruction pipelines with |
| Register external services as callable tools |
| List registered proxy integrations |
| Export Ed25519 public key for external signature verification |
Verification Gates (ERE)
Every output is checked by 5 deterministic passes before it leaves the system:
Pass | What it catches |
P1 | Empty or trivial responses |
P2 | "Not implemented" stubs, TODO placeholders |
P3 | Crypto operations in wrong language boundary |
P4 | Hardcoded secrets, unauthorized AI dependencies |
P5 | Structural integrity (unbalanced delimiters) |
If any pass fails, the output is BLOCKED. Not logged and forwarded — blocked. The gate is fail-closed.
Instruction Language (Magma)
Composable instructions with pipeline support:
§COMPUTE:FORGE:BUILD{query:"build a WORM handler in Rust"}Pipeline — chain operations:
§QUERY:ORACLE:SEARCH{q:"find auth patterns"} >> §SEAL:SENTINEL:ANCHOR{data:_prev}Verbs: COMPUTE (paid model) · QUERY (fast/free) · SEAL (sign + log) · DISPATCH (route to agent) · NULLIFY (void an action)
Every instruction is audit-logged with timestamp, executor, and signature.
Agent Routing
Define specialized agents with system prompts. Route tasks to the right expert:
const AGENT_PROMPTS = {
forge: "Production-grade builder. TypeScript, Rust, Haskell. Never stubs.",
oracle: "Knowledge graph. Citations. Never hallucinate sources.",
sentinel: "Zero-trust security. Hard verdicts: APPROVED or BLOCKED.",
vault: "Treasury. Basis points, yield curves, capital efficiency.",
}Add your own. Remove ours. The architecture doesn't care what agents you define — it cares that their output is verified and signed.
Provider Cascade
1. Bedrock (sovereign, paid, AWS credentials)
│ fails?
▼
2. Groq (fast, free tier)
│ fails?
▼
3. Ollama (local, bare metal, zero cost)
│ fails?
▼
Hard error — no silent degradationNo unverified fallback. No quiet failure. If all providers are down, you know immediately.
Integration
Claude Code / VSCode
Add to your .mcp.json:
{
"mcpServers": {
"sovereign": {
"command": "node",
"args": ["path/to/sovereign-mcp.mjs"]
}
}
}HTTP Client (any language)
curl -X POST http://localhost:7071 \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"compute_route","arguments":{"agent":"forge","query":"build a REST API"}}}'Verify Signatures Externally
import { verify } from 'crypto'
const pubkey = await fetch('http://localhost:7071', {
method: 'POST',
body: JSON.stringify({jsonrpc:'2.0',id:1,method:'tools/call',params:{name:'governor_pubkey',arguments:{}}})
}).then(r => r.json())
// Use pubkey to verify any response signatureArchitecture
sovereign-mcp/
├── sovereign-mcp.mjs Server (stdio + HTTP)
├── .env.example Provider configuration template
├── LICENSE [Your license here]
└── README.mdSingle file. No build step. No dependencies beyond @aws-sdk/client-bedrock-runtime (optional — only if you use Bedrock).
Who This Is For
Teams that need to prove what their AI said and when
Enterprises that can't send data to a third party
Developers building multi-model systems that don't break when one provider goes down
Anyone who thinks AI infrastructure should be auditable, not just "hopefully correct"
The Question
If your AI made a decision that cost you $10M, could you prove exactly what it said, when, and why?
If not, you don't have AI infrastructure. You have a hope and a prayer.
AI Infrastructure You Can Verify.
License
Functional Source License 1.1 — Ahmad Ali Parr / Bel Esprit D'Accord Trust
Change Date: 2030-07-24 · Change License: Apache 2.0
Use it. Build on it. Don't compete with it for 4 years.
SnapKitty Collective · 2026
Available Tools
7 toolsagent_dispatchA
Dispatch a task to a registered proxy tool or sovereign agent. Runs ERE gate before forwarding.
Inputs: target (required), payload (required).
compute_routeC
Route a query to the best available compute provider (Bedrock → Groq → Ollama). Returns result wrapped in Magma envelope.
Inputs: agent (required), query (required), max_tokens.
ere_verifyB
Run ERE 5-pass verification on a content string. Returns pass/fail per pod and METATRON certification.
Inputs: content (required), filepath.
governor_pubkeyA
Return the governor public key (base64 Ed25519 SPKI DER). Use this to verify Magma envelope signatures externally.
Inputs: no named parameters.
magma_execA
Execute a Magma instruction string. Parses §VERB:AGENT:ACTION{payload}, routes to the correct executor (COMPUTE→Bedrock, QUERY→Groq, SEAL→WORM, DISPATCH→proxy), signs result with governor Ed25519 key, and returns Magma envelope. Supports pipeline syntax with >>.
Inputs: instruction (required), verify_sig.
magma_sealB
Wrap any content in a Magma envelope with ERE verification and WORM hash.
Inputs: agent (required), content (required).
proxy_registerB
Register a named proxy tool at a URL. Proxied tools are callable via agent_dispatch.
Inputs: url (required), name (required), secret, description.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Tools have mostly clear boundaries, but `agent_dispatch` and `compute_route` could be confused for routing tasks, and `magma_exec` is a meta-tool that overlaps with several others. Still, descriptions are detailed enough to differentiate.
Names follow a consistent `<system>_<action>` pattern (e.g., `ere_verify`, `proxy_register`) except `compute_route` which reverses the order. Otherwise well-structured.
7 tools cover the core functionality without bloat. Each tool serves a distinct purpose and the set feels well-scoped for a sovereign computation system.
Covers primary operations (routing, verification, sealing, dispatch, execution, key retrieval). Missing explicit tools for verifying signatures or listing proxies, but the existing set handles core workflows.
Maintenance
Related MCP Connectors
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
AI governance MCP server for EU AI Act compliance and jurisdiction verification
MCP server for building and testing AI agents with multi-model experimentation and insights.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceCryptographic proof of every AI decision. An immutable, verifiable audit trail MCP server.1MIT
- FlicenseNot gradedqualityCmaintenanceAn MCP server that provides a self-improving knowledge graph with per-triple provenance and deterministic reasoning, enabling auditable, reproducible, and contradiction-aware answers for AI agents.-
- AlicenseBqualityCmaintenanceAn MCP server that enforces fail-closed deterministic checks, independent refute-first review, and tamper-evident hash-chained receipts for AI agent outputs before claiming completion.43MIT
- AlicenseAqualityBmaintenanceMCP server that provides cryptographic audit trails for AI agent actions, making every action tamper-evident via HMAC-SHA256 signed hash chains.10Apache 2.0