# Atomadic starter MCP (50 tools) (remote · mcp.atomadic.tech)

50 starter MCP tools for AI compliance and trust: identity, escrow, SLA, EU AI Act.

- Trust score: 58/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.atomadic.tech`: 58/100 (this document), [markdown](https://verifymcp.io/servers/atomadictech-aaaa-nexus/mcp-public.md), [page](https://verifymcp.io/servers/atomadictech-aaaa-nexus/mcp-public)

## Channel facts

- Endpoint: `https://mcp.atomadic.tech/mcp/public`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.5.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (escrow_release).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 2360 tokens (~47/item across 50 items; 50 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 29/100
  - Stability check failed: schema churn in the 9 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 12% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 50 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 51 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the Atomadic starter MCP (50 tools) server?

Atomadic starter MCP (50 tools) is a hosted endpoint at https://mcp.atomadic.tech/mcp/public, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http atomadictech-aaaa-nexus 'https://mcp.atomadic.tech/mcp/public'
```

### Cursor

```json
{
  "mcpServers": {
    "atomadictech-aaaa-nexus": {
      "url": "https://mcp.atomadic.tech/mcp/public"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "atomadictech-aaaa-nexus": {
      "type": "http",
      "url": "https://mcp.atomadic.tech/mcp/public"
    }
  }
}
```

### Codex

```toml
[mcp_servers.atomadictech-aaaa-nexus]
url = "https://mcp.atomadic.tech/mcp/public"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "atomadictech-aaaa-nexus": {
      "type": "remote",
      "url": "https://mcp.atomadic.tech/mcp/public",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add atomadictech-aaaa-nexus --url 'https://mcp.atomadic.tech/mcp/public' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  atomadictech-aaaa-nexus:
    url: "https://mcp.atomadic.tech/mcp/public"
```

### Netclaw

```json
{
  "McpServers": {
    "atomadictech-aaaa-nexus": {
      "Transport": "http",
      "Url": "https://mcp.atomadic.tech/mcp/public"
    }
  }
}
```

### Vellum

```bash
assistant mcp add atomadictech-aaaa-nexus -t streamable-http -u 'https://mcp.atomadic.tech/mcp/public'
```

### Other

```json
{
  "mcpServers": {
    "atomadictech-aaaa-nexus": {
      "type": "http",
      "url": "https://mcp.atomadic.tech/mcp/public"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 58, 0)

- [security regression] Stability: 0.27 → fail
- [security] Tool “compliance_check” rewrote its description, which is the text the model reads
- [functional regression] “compliance_check” dropped the required parameter “operation”
- [functional regression] “compliance_check” dropped the required parameter “jurisdiction”
- [functional regression] “compliance_check” dropped the required parameter “data_type”
- [functional] Schema quality: poor → fair
- [functional] Server version: 125 → 126
- [cosmetic] “compliance_check” added an optional parameter “kl_divergence”
- [cosmetic] “compliance_check” added an optional parameter “description”
- [cosmetic] “compliance_check” added an optional parameter “chain_depth”

### 2026-11-04 (score 58, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Server version: 124 → 125

### 2026-11-03 (score 57, 0)

- [functional] Server version: 0.6.9 → 124

### 2026-11-02 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 55, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 54, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-27 (score 54)

First indexed and scored.

## MCP tools (50)

### `murmuration` (~97 tokens)

Murmuration

START HERE (free, no key). Initialize your Atomadic control surface in one call: returns a verbose, step-by-step setup (SDK install, MCP connect, your unlocked tools), a RUNNABLE polyglot demo that proves the superpowers, recon links, and a one-command bootstrap. Idempotent — re-call anytime to re-check.

Input parameters:

- `agent_id` (string): Optional stable id to track your onboarding state across calls.

### `agents_contradiction` (~50 tokens)

Agents Contradiction

[agents] Detect contradictions between two free-text agent outputs (natural-language claim drift). For structured key/value claims that must agree, use detect_contradiction instead.

Input parameters:

- `statements` (array, required)

### `agents_semantic_diff` (~67 tokens)

Agents Semantic Diff

[agents] Semantic diff between two free-text agent outputs (meaning-level change, not text-level). Use forge_verify for build artifacts and drift_check for certified operational drift.

Input parameters:

- `context` (string)
- `output_a` (string, required)
- `output_b` (string, required)

### `agents_register` (~30 tokens)

Agents Register

[agents] Register an agent

Input parameters:

- `agent_id` (string, required)
- `capabilities` (array, required)

### `agents_reputation` (~26 tokens)

Agents Reputation

[agents] Agent reputation and trust score

Input parameters:

- `agent_id` (string, required)

### `agents_plan` (~44 tokens)

Agents Plan

[agents] Autonomous agent goal planning

Input parameters:

- `constraints` (object): Optional constraints for the plan (e.g., time limits, resource caps)
- `goal` (string, required)

### `reputation_record` (~47 tokens)

Reputation Record

[agents] Record agent interaction

Input parameters:

- `agent_id` (string, required)
- `counterparty_id` (string)
- `interaction_type` (string, required)
- `outcome` (string, required)

### `sla_register` (~38 tokens)

Sla Register

[agents] Register an SLA

Input parameters:

- `consumer_id` (string, required)
- `provider_id` (string, required)
- `terms` (object, required)

### `sla_report` (~38 tokens)

Sla Report

[agents] Report SLA violation

Input parameters:

- `description` (string)
- `sla_id` (string, required)
- `violation_type` (string, required)

### `swarm_inbox` (~16 tokens)

Swarm Inbox

[agents] Poll swarm inbox

### `swarm_relay` (~44 tokens)

Swarm Relay

[agents] Relay message through swarm

Input parameters:

- `message` (object, required)
- `target_agent_id` (string, required)
- `ttl` (integer): Hop limit for relay

### `compliance_check` (~147 tokens)

Compliance Check

[security] Delegation-depth + KL gate (GOV-100). Reads chain_depth and kl_divergence. It does NOT read your data description and does NOT evaluate GDPR/CCPA - compliant:true only means the delegation chain is shallow and KL is under epsilon.

Input parameters:

- `chain_depth` (integer): Delegation chain depth. Higher = deeper hand-off. Past the gate threshold the result escalates to quarantine_escalation.
- `description` (string): Free text. Accepted for readability and IGNORED by the gate. It never changes the verdict.
- `kl_divergence` (number): eps_KL divergence of the current policy from baseline. Above epsilon fails the gate.

### `compliance_eu_ai_act` (~45 tokens)

Compliance Eu Ai Act

[security] EU AI Act compliance certificate

Input parameters:

- `intended_purpose` (string, required)
- `risk_category` (string, required)
- `system_id` (string, required)

### `compliance_explain` (~48 tokens)

Compliance Explain

[security] Explainability certificate (XPL-100-ExplainBound)

Input parameters:

- `decision_id` (string, required)
- `model_id` (string, required)
- `subject_context` (object, required)

### `compliance_fairness` (~57 tokens)

Compliance Fairness

[security] Fairness proof (FNS-100-FairnessBound)

Input parameters:

- `dataset_id` (string, required)
- `metric` (string, required)
- `model_id` (string, required)
- `protected_attrs` (array, required)

### `compliance_lineage` (~39 tokens)

Compliance Lineage

[security] Data lineage (LIN-100-ChainIntegrity)

Input parameters:

- `dataset_stages` (array, required)
- `model_id` (string, required)

### `compliance_transparency` (~37 tokens)

Compliance Transparency

[security] Transparency report

Input parameters:

- `include` (array, required)
- `period` (string, required)
- `system_id` (string, required)

### `compliance_incident` (~46 tokens)

Compliance Incident

[security] Report compliance incident

Input parameters:

- `affected_users` (integer, required)
- `description` (string, required)
- `severity` (string, required)
- `system_id` (string, required)

### `compliance_incidents` (~23 tokens)

Compliance Incidents

[security] Incident registry

Input parameters:

- `system_id` (string, required)

### `compliance_oversight` (~47 tokens)

Compliance Oversight

[security] Log oversight event

Input parameters:

- `decision` (string, required)
- `notes` (string, required)
- `reviewer_id` (string, required)
- `system_id` (string, required)

### `security_zero_day` (~31 tokens)

Security Zero Day

[security] Zero-day threat assessment

Input parameters:

- `context` (object)
- `target` (string, required)

### `threat_score` (~31 tokens)

Threat Score

[security] Multi-vector threat score

Input parameters:

- `agent_id` (string, required)
- `context` (string)

### `defi_optimize` (~48 tokens)

Defi Optimize

[defi] LP parameter optimization (DFP-100-OptimalTick)

Input parameters:

- `position` (object, required)
- `protocol` (string, required)
- `risk_tolerance` (number, required)

### `defi_risk_score` (~50 tokens)

Defi Risk Score

[defi] DeFi risk scoring (DFI-101-RiskScoreBound)

Input parameters:

- `market_conditions` (object, required)
- `position` (object, required)
- `protocol` (string, required)

### `defi_yield_optimize` (~45 tokens)

Defi Yield Optimize

[defi] Yield Oracle (YLD-100-YieldConvergence)

Input parameters:

- `principal_usd` (number, required)
- `risk_tolerance` (number, required)

### `escrow_create` (~56 tokens)

Escrow Create

[defi] Create agent-to-agent escrow

Input parameters:

- `amount` (number, required)
- `conditions` (object)
- `currency` (string, required)
- `payee_id` (string, required)
- `payer_id` (string, required)

### `escrow_release` (~25 tokens)

Escrow Release

[defi] Release escrowed funds

Input parameters:

- `escrow_id` (string, required)

### `escrow_dispute` (~39 tokens)

Escrow Dispute

[defi] Open escrow dispute

Input parameters:

- `escrow_id` (string, required)
- `evidence` (object)
- `reason` (string, required)

### `forge_badge` (~32 tokens)

Forge Badge

[fuse] Model quality badge

Input parameters:

- `model` (string, required): Model id to fetch the quality badge for.

### `forge_leaderboard` (~17 tokens)

Forge Leaderboard

[fuse] Model leaderboard

### `forge_verify` (~33 tokens)

Forge Verify

[fuse] Verify a model submission

Input parameters:

- `model_id` (string, required)
- `verification_type` (string)

### `forge_delta_submit` (~40 tokens)

Forge Delta Submit

[fuse] Submit a model delta

Input parameters:

- `delta` (object, required)
- `description` (string)
- `model_id` (string, required)

### `identity_verify` (~24 tokens)

Identity Verify

[identity] Topological identity verification

Input parameters:

- `agent_id` (string, required)

### `identity_sybil_check` (~19 tokens)

Identity Sybil Check

[identity] Sybil-resistance check

### `ratchet_register` (~28 tokens)

Ratchet Register

[identity] RatchetGate — register session

Input parameters:

- `session_id` (string, required)

### `ratchet_advance` (~29 tokens)

Ratchet Advance

[identity] RatchetGate — advance session

Input parameters:

- `session_id` (string, required)

### `inference` (~25 tokens)

Inference

[inference] Chat inference with hallucination guard

Input parameters:

- `messages` (array, required)

### `inference_stream` (~27 tokens)

Inference Stream

[inference] Streaming inference with chain-of-thought

Input parameters:

- `messages` (array, required)

### `rag_augment` (~18 tokens)

Rag Augment

[inference] Trusted RAG augmentation

### `text_summarize` (~25 tokens)

Text Summarize

[inference] Text summarization

Input parameters:

- `text` (string, required)

### `rng_quantum` (~19 tokens)

Rng Quantum

[inference] Quantum random number with proof

### `rng_verify` (~18 tokens)

Rng Verify

[inference] Verify current epoch random value

### `trust_score` (~24 tokens)

Trust Score

[trust] Bounded trust score

Input parameters:

- `agent_id` (string, required)

### `drift_check` (~48 tokens)

Drift Check

[trust] DriftGuard check (DRG-100-DriftBound)

Input parameters:

- `current_window` (object, required)
- `model_id` (string, required)
- `reference_window` (object, required)

### `drift_certificate` (~21 tokens)

Drift Certificate

[trust] Drift certificate

Input parameters:

- `id` (string, required)

### `oracle_hallucination` (~33 tokens)

Oracle Hallucination

[trust] Hallucination oracle

Input parameters:

- `claim` (string, required)
- `context` (string)

### `audit_work_claim` (~131 tokens)

Audit Work Claim

[Ledger product, entitlement: ledger] Recompute-audit an agent work claim: re-derive a deterministic SHA-256 digest from the claimed inputs and check it against the claimed digest. Returns GREEN (matches), RED (tampered), or UNVERIFIED (no claim supplied). Replay, not opinion. 3 free calls/day, then entitlement 'ledger'.

Input parameters:

- `claimed_digest` (string): The agent's claimed SHA-256 digest to verify against. Omit for UNVERIFIED + the recomputed digest.
- `inputs` (object, required): The work/claim payload to recompute a digest over.

### `verify_settlement` (~85 tokens)

Verify Settlement

[Ledger product, entitlement: ledger] Proof-gated settlement: recompute the work digest and authorize a payout only if the claimed digest verifies GREEN. No proof, no payout. 3 free calls/day, then entitlement 'ledger'.

Input parameters:

- `claimed_digest` (string): Claimed digest the payout is conditioned on.
- `inputs` (object, required): The work payload backing the settlement.

### `detect_contradiction` (~95 tokens)

Detect Contradiction

[Ledger product, entitlement: ledger] Detect contradictions across structured claims: the same key asserted with conflicting values flips RED, otherwise GREEN. Deterministic and recomputable. Use agents_contradiction instead when comparing free-text agent prose. 3 free calls/day, then entitlement 'ledger'.

Input parameters:

- `claims` (array, required): List of claim objects, each with a 'key' (or 'subject') and a 'value'.

### `render_polyglot_all_pure` (~81 tokens)

Render Polyglot All Pure

[Fuse product · entitlement: fuse · FREE_R2_DEMO] Polyglot emit to all 7 supported targets in one call. Returns {ok, ir, results, languages}. Canonical demo examples baked to R2; novel inputs via SDK.

Input parameters:

- `atom_name` (string, required)
- `source_text` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/atomadictech-aaaa-nexus/mcp-public#diagnostics

## Score history

- 2026-11-05: 58
- 2026-11-04: 58
- 2026-11-03: 57
- 2026-11-02: 57
- 2026-11-01: 56
- 2026-10-31: 56
- 2026-10-30: 55
- 2026-10-29: 55
- 2026-10-28: 54
- 2026-10-27: 54

## Common questions

### What is the Atomadic starter MCP (50 tools) server?

Atomadic starter MCP (50 tools) is listed in the public MCP registry as io.github.atomadictech/aaaa-nexus. 50 starter MCP tools for AI compliance and trust: identity, escrow, SLA, EU AI Act. This page covers its hosted endpoint (https://mcp.atomadic.tech/mcp/public).

### Is the Atomadic starter MCP (50 tools) server safe to use?

Atomadic starter MCP (50 tools) scores 58 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Atomadic starter MCP (50 tools) server expose?

Atomadic starter MCP (50 tools) exposes 50 tools: murmuration, agents_contradiction, agents_semantic_diff, agents_register, agents_reputation, and 45 more. Their descriptions and schemas cost roughly 2,183 tokens of context every time the server is loaded.

### Does the Atomadic starter MCP (50 tools) server require authentication?

No. We connected to Atomadic starter MCP (50 tools) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Atomadic starter MCP (50 tools) server still maintained?

Atomadic starter MCP (50 tools) is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.atomadic.tech/mcp/public
- Repository: https://github.com/atomadictech/atomadic-mcp
- Website: https://atomadic.tech/
- Changelog RSS feed: https://verifymcp.io/servers/atomadictech-aaaa-nexus/mcp-public.xml
- Changelog JSON feed: https://verifymcp.io/servers/atomadictech-aaaa-nexus/mcp-public.json
- HTML version of this page: https://verifymcp.io/servers/atomadictech-aaaa-nexus/mcp-public