Connect Atomadic starter MCP (50 tools) and your agent gets 44 tools, among them aegis_mcp_proxy_execute, aegis_router_epistemic_bound, agents_plan. It answers at https://mcp.atomadic.tech/mcp/public over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 21 October 2026, succeeded.
Formally verified AI safety APIs. Pay-per-call via USDC (x402). 75+ endpoints, no signup.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
aegis_mcp_proxy_execute | NEXUS AEGIS MCP-Sentinel gateway for prompt-injection resistant tool execution Inputs: body |
aegis_router_epistemic_bound | NEXUS AEGIS reverse proxy that blocks high-entropy or low-confidence generations Inputs: body |
agents_plan | Rule-based goal decomposition into 3–5 deterministic execution steps. Inputs: body |
authorize_action | Pre-action authorization gateway — deterministic tool-call gating with cryptographic tokens Inputs: body |
certify_codebase | Countersign local Forge certificate with storefront attestation lane. Inputs: body |
certify_output | Output certification notary — tamper-evident seal on agent deliverables. Inputs: body |
contract_verify | Behavioral contract verifier — verify agent policy claims against formal bounds Inputs: body |
docs_generate | Deterministic documentation enrichment targets from local path analysis. Inputs: body |
entitlement_attest | Attest Ed25519-style entitlement token structure + signature for sovereign emit access. Inputs: body |
federation_mint | Agent identity federation — mint cross-platform portable identity tokens Inputs: body |
forge_audit | Compound Forge audit — recon + certify + wire in one deterministic pass. Inputs: body |
forge_certify | Polyglot 4-axis certify (docs/tests/layout/wire) with scored verdict. Inputs: body |
forge_recon | Polyglot repo recon — language/tier/source breakdown for monadic architectures. Inputs: body |
forge_tier_infer | Infer monadic tier placement for a file path from polyglot heuristics. Inputs: body |
forge_wire | Repo-wide upward-import wire scan — polyglot tier discipline check. Inputs: body |
hallucination_oracle | Get the LLM hallucination threshold constant Inputs: body |
identity_verify | Topological identity verification Inputs: body |
intent_classify | Keyword intent classifier for agent utterances — query/command/report/alert lanes. Inputs: body |
keys_validate | Validate X-API-Key entitlement tier (paid/extended/master) before gated tool calls. Inputs: body |
lineage_record | Decision lineage vault — structured decision trace capture with tamper-proof hash chain Inputs: body |
lint_analyze | Synthesize lint findings from supplied local analysis artifacts. Inputs: body |
omega_emit_materialize | Materialize deterministic contract sketch from intent — logic upstream of language. Inputs: body |
omega_emit_polyglot | Language-agnostic emit targets from frozen contract — Python/Rust/TS/JS/Go sketches. Inputs: body |
omega_intent_nl | Structured intent → agent-facing NL sketch (training signal, not human blueprint). Inputs: body |
omega_intent_route | Rank sovereign intent lanes (recon/emit/heal/govern/hive/synthesis) — deterministic router. Inputs: body |
rag_augment | Trusted RAG augment — retrieve-and-quote augmentation with provenance hashes. Inputs: body |
ratchet_register | Register a new 47-epoch RatchetGate session (MCP CVE-2025-6514 mitigation) Inputs: body |
rng_quantum | Quantum-seeded random bytes with HMAC-SHA256 entropy proof Inputs: body |
spending_authorize | Spending governance — validate agent chain spending within trust-decay bounds Inputs: body |
sys_constants | Sys constants snapshot — public tier counts, trust floor, and block dimension anchors. Inputs: body |
sys_lint_gate | Sys lint gate — structural policy lint over JSON agent plans. Inputs: body |
sys_trust_gate | Sys trust gate — PASS/FAIL hallucination and drift screen for agent payloads. Inputs: body |
text_summarize | Extractive text summarizer for bounded passages (JSON in, summary out). Inputs: body |
threat_score | Score a JSON payload for security threats using triality consensus Inputs: body |
uep_aha_detect | UEP AHA moment detector — novelty spike scoring for epiphany-style gates. Inputs: body |
uep_autopoiesis_plan | UEP autopoiesis plan — structured self-maintenance loop proposal with rollback hooks. Inputs: body |
uep_context | UEP context pack synthesis — merge recon snippets into a single agent-facing context object. Inputs: body |
uep_preflight | UEP phase-0 preflight gate — bounded task summary and friction estimate before execution. Inputs: body |
uep_synthesis_guard | UEP synthesis guard — block ungrounded expansions when evidence links are missing. Inputs: body |
uep_trace_certify | UEP trace certification — sign a decision trace checksum for audit vault handoff. Inputs: body |
vanguard_continuous_redteam, vanguard_escrow_lock_and_verify, vanguard_mev_route_intent, vanguard_wallet_govern_session
Every block below points at https://mcp.atomadic.tech/mcp/public. Pick your client and copy.
claude mcp add --transport http atomadic-starter-mcp-50-tools https://mcp.atomadic.tech/mcp/public
{
"mcpServers": {
"atomadic-starter-mcp-50-tools": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.atomadic.tech/mcp/public"]
}
}
}{
"mcpServers": {
"atomadic-starter-mcp-50-tools": {
"url": "https://mcp.atomadic.tech/mcp/public"
}
}
}{
"servers": {
"atomadic-starter-mcp-50-tools": {
"type": "http",
"url": "https://mcp.atomadic.tech/mcp/public"
}
}
}{
"context_servers": {
"atomadic-starter-mcp-50-tools": {
"url": "https://mcp.atomadic.tech/mcp/public"
}
}
}{
"mcpServers": {
"atomadic-starter-mcp-50-tools": {
"serverUrl": "https://mcp.atomadic.tech/mcp/public"
}
}
}{
"mcpServers": {
"atomadic-starter-mcp-50-tools": {
"url": "https://mcp.atomadic.tech/mcp/public"
}
}
}name: Atomadic starter MCP (50 tools)
version: 0.0.1
schema: v1
mcpServers:
- name: Atomadic starter MCP (50 tools)
type: streamable-http
url: https://mcp.atomadic.tech/mcp/public{
"mcpServers": {
"atomadic-starter-mcp-50-tools": {
"httpUrl": "https://mcp.atomadic.tech/mcp/public"
}
}
}{
"mcpServers": {
"atomadic-starter-mcp-50-tools": {
"type": "http",
"url": "https://mcp.atomadic.tech/mcp/public"
}
}
}{
"mcpServers": {
"atomadic-starter-mcp-50-tools": {
"url": "https://mcp.atomadic.tech/mcp/public"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.atomadic.tech%2Fmcp%2Fpublic&type=streamable_http&id=atomadic-starter-mcp-50-tools&name=Atomadic%20starter%20MCP%20%2850%20tools%29
It answered our last check on 21 October 2026 in 251 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
44, as returned by the server's own tools/list on 13 September 2026: aegis_mcp_proxy_execute, aegis_router_epistemic_bound, agents_plan, authorize_action, certify_codebase, certify_output, contract_verify, docs_generate, and 36 more.
It answered our last check on 21 October 2026 in 251 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.atomadic.tech/mcp/public. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.atomadictech. Endpoint host: mcp.atomadic.tech. ARD identifier: urn:air:io.github.atomadictech:mcp:aaaa-nexus.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.