# Atomadic MCP

> Atomadic MCP: 68 deterministic tools for agent identity, escrow, SLA, EU AI Act compliance.

- name: tech.atomadic/atomadic
- version: 0.6.9
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/tech.atomadic%2Fatomadic
- tools: https://api.protogrid.dev/v1/servers/tech.atomadic%2Fatomadic/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "atomadic": {
      "type": "http",
      "url": "https://mcp.atomadic.tech/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-2d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: agents_intent_classify (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); identity_verify (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); oracle_entropy (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 4,194 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 1 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 68, about 4,194 tokens to load them all
- tool set hash: 4d25ad0de3ff710decca3a9841deaf74
- badge: [![protogrid quality](https://protogrid.dev/badge/tech.atomadic/atomadic.svg)](https://protogrid.dev/servers/tech.atomadic/atomadic)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.atomadic.tech/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (68)

- `agents_contradiction`: [agents] Detect contradictions in agent outputs
- `agents_intent_classify`: [agents] Agent intent classification
- `agents_plan`: [agents] Autonomous agent goal planning
- `agents_register`: [agents] Register an agent
- `agents_reputation`: [agents] Agent reputation and trust score
- `agents_semantic_diff`: [agents] Semantic diff between agent outputs
- `agents_topology`: [agents] Live swarm topology
- `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'.
- `compliance_check`: [security] GDPR/CCPA compliance gate
- `compliance_eu_ai_act`: [security] EU AI Act compliance certificate
- `compliance_explain`: [security] Explainability certificate (XPL-100-ExplainBound)
- `compliance_fairness`: [security] Fairness proof (FNS-100-FairnessBound)
- `compliance_incident`: [security] Report compliance incident
- `compliance_incidents`: [security] Incident registry
- `compliance_lineage`: [security] Data lineage (LIN-100-ChainIntegrity)
- `compliance_oversight`: [security] Log oversight event
- `compliance_oversight_history`: [security] Oversight history
- `compliance_transparency`: [security] Transparency report
- `defi_bridge_verify`: [defi] Bridge Proof (BRP-100-BridgeIntegrity)
- `defi_contract_audit`: [defi] Contract Verify (CVR-100-AuditBound)
- `defi_liquidation_check`: [defi] Liquid Shield (LQS-100-LiquidationBound)
- `defi_optimize`: [defi] LP parameter optimization (DFP-100-OptimalTick)
- `defi_oracle_verify`: [defi] Oracle guard (OGD-100-ManipulationBound)
- `defi_risk_score`: [defi] DeFi risk scoring (DFI-101-RiskScoreBound)
- `defi_yield_optimize`: [defi] Yield Oracle (YLD-100-YieldConvergence)
- `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. 3 free calls/day, then entitlement 'ledger'.
- `drift_certificate`: [trust] Drift certificate
- `drift_check`: [trust] DriftGuard check (DRG-100-DriftBound)
- `enforce_sla`: [Ledger product, entitlement: ledger] Enforce an SLA/obligation by recomputation: the obligation is met only if the work verifies GREEN against its claimed digest. 3 free calls/day, then entitlement 'ledger'.
- `escrow_create`: [defi] Create agent-to-agent escrow
- `escrow_dispute`: [defi] Open escrow dispute
- `escrow_release`: [defi] Release escrowed funds
- `forge_badge_{model}`: [fuse] Model quality badge
- `forge_delta_submit`: [fuse] Submit a model delta
- `forge_leaderboard`: [fuse] Model leaderboard
- `forge_quarantine`: [fuse] Quarantined models
- `forge_verify`: [fuse] Verify a model submission
- `identity_sybil_check`: [identity] Sybil-resistance check
- `identity_verify`: [identity] Topological identity verification
- `inference`: [inference] Chat inference with hallucination guard
- `inference_stream`: [inference] Streaming inference with chain-of-thought
- `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.
- `oracle_entropy`: [trust] Entropy epoch oracle
- `oracle_hallucination`: [trust] Hallucination oracle
- `rag_augment`: [inference] Trusted RAG augmentation
- `ratchet_advance`: [identity] RatchetGate — advance session
- `ratchet_probe`: [identity] RatchetGate — health probe
- `ratchet_register`: [identity] RatchetGate — register session
- `receipt_reputation`: [Ledger product, entitlement: ledger] Compute an agent's reputation from a ledger of verifiable receipts (verified minus refuted), deterministically - not from vibes or LLM judgment. 3 free calls/day, then entitlement 'ledger'.
- `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.
- `render_polyglot_roundtrip_pure`: [Fuse product · entitlement: fuse · FREE_R2_DEMO] Syntax-as-Data polyglot render head: source -> language-neutral logic IR -> source in target language. Canonical demo examples baked to R2 (4 examples × 12 languages). Live emit of novel inputs via the SDK.
- `reputation_record`: [agents] Record agent interaction
- `rng_quantum`: [inference] Quantum random number with proof
- `rng_verify`: [inference] Verify current epoch random value
- `route_capability`: [Ledger product, entitlement: ledger] Route a natural-language intent to a deterministic capability/pipeline coordinate. 3 free calls/day, then entitlement 'ledger'.
- `security_zero_day`: [security] Zero-day threat assessment
- `sla_register`: [agents] Register an SLA
- `sla_report`: [agents] Report SLA violation
- `swarm_inbox`: [agents] Poll swarm inbox
- `swarm_relay`: [agents] Relay message through swarm
- `text_keywords`: [inference] Keyword extraction
- `text_sentiment`: [inference] Sentiment analysis
- `text_summarize`: [inference] Text summarization
- `threat_score`: [security] Multi-vector threat score
- `trust_decay`: [trust] Current trust ceiling value
- `trust_history`: [trust] Trust score history
- `trust_score`: [trust] Bounded trust score
- `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'.