# Atomadictech Atomadic Forge MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.atomadictech%2Fatomadic-forge
Registry id: `mcp-registry/io.github.atomadictech/atomadic-forge`
Status: live (checked 2026-11-22T13:57:36.739Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 3525
- Outages (90 days): 0

## Install

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

Claude Code:

```sh
claude mcp add --transport http atomadictech-atomadic-forge-mcp-server https://forge.atomadic.tech/mcp
```

## Tools (68)

- `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_c
- `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 two free-text agent outputs (meaning-level change, not text-level). Use forge_verify for build artifacts and drift_check for cert
- `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
- `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 - c
- `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. 
- `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 dige
- `escrow_create`: [defi] Create agent-to-agent escrow
- `escrow_dispute`: [defi] Open escrow dispute
- `escrow_release`: [defi] Release escrowed funds
- `forge_badge`: [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 
- `oracle_entropy`: [trust] Entropy epoch oracle
- `oracle_hallucination`: [trust] Hallucination oracle
- `rag_augment`: [inference] Trusted RAG augmentation
- `ratchet_advance`: [identity] RatchetGate â€” advance session
- `ratchet_probe`: [identity] RatchetGate â€” health probe
- `ratchet_register`: [identity] RatchetGate â€” 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 
- `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 exa
- `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. Canonic
- `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 'led
- `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 pro

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
