Atomadic Nexus MCP server

Read from the package source without running it. The installed server may list more.

• agent_plan

  Generate a trust-gated execution plan for a goal. Decomposes into verified sub-tasks.

• agent_reputation

  Per-agent reputation score (ERC-8004 compatible). Cumulative trust history.

• agent_topology

  Get the current agent swarm topology — nodes, edges, trust scores, delegation chains.

• attest_lineage

  Attest provenance chain for an artifact. Links parent SHAs to form immutable lineage.

• consensus_createwrite action

  Create a consensus round among peer agents. Requires threshold agreement to pass.

• contradiction_detect

  Detect logical contradictions between two statements. Returns contradiction score + evidence.

• delegation_depth

  Check current delegation depth against D_MAX=23 limit. Prevents unbounded recursion.

• drift_check

  Detect distribution drift in agent outputs. Returns drift magnitude + corrective signal.

• emergent_behavior_probe

  Probe for emergent/deceptive behavior patterns in an agent loop trace.

• escrow_open

  Open a USDC escrow between buyer and seller agents. Returns escrow_id + conditions.

• goal_alignment_check

  Check if planned actions align with stated intent. Detects goal drift and misalignment.

• hallucination_oracle

  Hallucination probe with certified confabulation bound (epsilon_KL anchored).

• lora_capture_fix

  Capture a before/after fix pair for LoRA fine-tuning. Label describes the correction type.

• nexus_shield

  Inline guardrail combo: trust + injection + hallucination check in sub-200ms.

• pricing_lookup

  Look up pricing for an Atomadic product. Returns tiers, features, and current rates.

• prompt_inject_scan

  Scan a prompt for injection attacks. Returns threat level + extraction vectors found.

• ratchet_gate

  Session re-key gate (CVE-2025-6514 patched). Advances session trust ratchet.

• recall_lineage

  Recall the full provenance chain for an artifact by its SHA.

• reputation_ledger

  Full reputation ledger for an agent — every attestation, penalty, and trust event.

• routing_recommend

  Recommend optimal agent routing for a request based on trust, capability, and load.

• semantic_diff

  Compute semantic difference between two texts. Returns similarity score + divergence vectors.

• sign_x402

  Generate x402 payment-proof headers (stub — supply real EIP-712 signer in production).

• sla_engine

  Evaluate an SLA contract. Returns compliance score + violations + remediation.

• stripe_link

  Generate a Stripe payment link for a subscription tier (starter/pro/team).

• tool_misuse_detect

  Detect potential tool misuse — unusual args, privilege escalation, scope violations.

• topological_identity

  Verify topological identity of an agent from its fingerprint. Lattice-anchored.

• trust_gate

  Classify + score a request. Returns verdict (PASS/REFINE/QUARANTINE/REJECT) + Codex-anchored confidence.

• trust_phase_oracle

  Get the current trust phase for an agent (bootstrap/establishing/mature/sovereign).

• trust_score

  Get cumulative trust score for an agent. Anchored to TAU_TRUST = 1820/1823.

• veridelegate

  Verify a UCAN delegation chain. Returns validity + delegation depth + capabilities.

• verirand

  Cryptographic verifiable randomness (VRF-grade). Returns hex + proof.

• x402_verify

  Verify an x402 payment-proof header (EIP-712 signed, USDC on Base).

• Code scan8 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancerepository not readable: repo not found3/15
• Maintainer identityno repository or website to verify2/10

Safety score

65/100

higher than 25% of 4,460 AI and agents servers

Tools

32

the typical AI and agents server has 6

Tools that change things

3%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

31

more than 18% of 1,538 AI and agents servers with a package

Atomadic Nexus: common questions

Is Atomadic Nexus MCP server safe?

With care: it is graded C, so read the findings first (65/100). Read the Atomadic Nexus safety report

How do I install Atomadic Nexus?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Atomadic Nexus need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Atomadic Nexus maintained?

The latest release is v0.1.1.

What can I use instead of Atomadic Nexus?

Servers from other publishers that do the same job: agent-device MCP server, Agent Recall MCP server and Decionis Commerce Gate MCP server.

How does Atomadic Nexus compare with other AI and agents MCP servers?

safety score 65/100 (higher than 25% of 4,460 AI and agents servers); tools 32 (the typical AI and agents server has 6); tools that change things 3% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.