Skip to content

Atomadic starter MCP (50 tools)

io.github.atomadictech/aaaa-nexusatomadictechstreamable-httpv0.5.2Scanned

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

50 tools: 2 can delete or cancel things, 1 do something that can't be undone, 44 change things and 3 only read.

Tools: 2 delete, 1 irreversible, 44 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Atomadic starter MCP (50 tools) can do

The Atomadic starter MCP (50 tools) is published by the GitHub account atomadictech. It has 50 tools. It can delete or cancel things (2 tools: escrow_release and escrow_dispute), do things that cannot be undone, such as sending, paying or publishing (escrow_create) and create or change data (44 tools: murmuration, agents_contradiction, agents_register, agents_reputation and 40 more). 3 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 0.5.2.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

50 tools

Deletes or cancels 2Claude Code: deny
  • escrow_dispute[defi] Open escrow disputeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    [defi] Open escrow dispute

    Annotations the server declares

    • title: Escrow Dispute
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
  • escrow_release[defi] Release escrowed fundsNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    [defi] Release escrowed funds

    Annotations the server declares

    • title: Escrow Release
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Can't be undone 1Claude Code: ask
  • escrow_create[defi] Create agent-to-agent escrowNo findings

    Why it is in this group

    • The name "escrow_create" says "create": a word for a change.
    • The input carries an amount (input.amount) and a currency, so it moves money.
    Description, as the server wrote it
    [defi] Create agent-to-agent escrow

    Annotations the server declares

    • title: Escrow Create
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 44Claude Code: ask
  • agents_contradiction[agents] Detect contradictions between two free-text agent outputs (natural-language claim drift).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [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.

    Annotations the server declares

    • title: Agents Contradiction
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • agents_plan[agents] Autonomous agent goal planningNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [agents] Autonomous agent goal planning

    Annotations the server declares

    • title: Agents Plan
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • agents_register[agents] Register an agentNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [agents] Register an agent

    Annotations the server declares

    • title: Agents Register
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • agents_reputation[agents] Agent reputation and trust scoreNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [agents] Agent reputation and trust score

    Annotations the server declares

    • title: Agents Reputation
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [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'.

    Annotations the server declares

    • title: Audit Work Claim
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compliance_check[security] Delegation-depth + KL gate (GOV-100).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [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.

    Annotations the server declares

    • title: Compliance Check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compliance_eu_ai_act[security] EU AI Act compliance certificateNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [security] EU AI Act compliance certificate

    Annotations the server declares

    • title: Compliance Eu Ai Act
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compliance_fairness[security] Fairness proof (FNS-100-FairnessBound)No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [security] Fairness proof (FNS-100-FairnessBound)

    Annotations the server declares

    • title: Compliance Fairness
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compliance_incident[security] Report compliance incidentNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [security] Report compliance incident

    Annotations the server declares

    • title: Compliance Incident
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • compliance_incidents[security] Incident registryNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [security] Incident registry

    Annotations the server declares

    • title: Compliance Incidents
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compliance_lineage[security] Data lineage (LIN-100-ChainIntegrity)No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [security] Data lineage (LIN-100-ChainIntegrity)

    Annotations the server declares

    • title: Compliance Lineage
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compliance_oversight[security] Log oversight eventNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [security] Log oversight event

    Annotations the server declares

    • title: Compliance Oversight
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compliance_transparency[security] Transparency reportNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [security] Transparency report

    Annotations the server declares

    • title: Compliance Transparency
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • defi_optimize[defi] LP parameter optimization (DFP-100-OptimalTick)No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [defi] LP parameter optimization (DFP-100-OptimalTick)

    Annotations the server declares

    • title: Defi Optimize
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • defi_risk_score[defi] DeFi risk scoring (DFI-101-RiskScoreBound)No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [defi] DeFi risk scoring (DFI-101-RiskScoreBound)

    Annotations the server declares

    • title: Defi Risk Score
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • defi_yield_optimize[defi] Yield Oracle (YLD-100-YieldConvergence)No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [defi] Yield Oracle (YLD-100-YieldConvergence)

    Annotations the server declares

    • title: Defi Yield Optimize
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • detect_contradiction[Ledger product, entitlement: ledger] Detect contradictions across structured claims: the same key asserted with conflicting values flips RED, otherwise GREEN.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [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'.

    Annotations the server declares

    • title: Detect Contradiction
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • drift_certificate[trust] Drift certificateNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [trust] Drift certificate

    Annotations the server declares

    • title: Drift Certificate
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • drift_check[trust] DriftGuard check (DRG-100-DriftBound)No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [trust] DriftGuard check (DRG-100-DriftBound)

    Annotations the server declares

    • title: Drift Check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • forge_badge[fuse] Model quality badgeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [fuse] Model quality badge

    Annotations the server declares

    • title: Forge Badge
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • forge_delta_submit[fuse] Submit a model deltaNo findings

    Why it is in this group

    • The name "forge_delta_submit" says "submit": a word for a change.
    Description, as the server wrote it
    [fuse] Submit a model delta

    Annotations the server declares

    • title: Forge Delta Submit
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • forge_leaderboard[fuse] Model leaderboardNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [fuse] Model leaderboard

    Annotations the server declares

    • title: Forge Leaderboard
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • forge_verify[fuse] Verify a model submissionNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [fuse] Verify a model submission

    Annotations the server declares

    • title: Forge Verify
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • identity_sybil_check[identity] Sybil-resistance checkNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [identity] Sybil-resistance check

    Annotations the server declares

    • title: Identity Sybil Check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • identity_verify[identity] Topological identity verificationNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [identity] Topological identity verification

    Annotations the server declares

    • title: Identity Verify
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • inference[inference] Chat inference with hallucination guardNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [inference] Chat inference with hallucination guard

    Annotations the server declares

    • title: Inference
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • inference_stream[inference] Streaming inference with chain-of-thoughtNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [inference] Streaming inference with chain-of-thought

    Annotations the server declares

    • title: Inference Stream
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • murmurationSTART HERE (free, no key).No findings

    Why it is in this group

    • The description's first verb is "start": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Murmuration
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • oracle_hallucination[trust] Hallucination oracleNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [trust] Hallucination oracle

    Annotations the server declares

    • title: Oracle Hallucination
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • rag_augment[inference] Trusted RAG augmentationNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [inference] Trusted RAG augmentation

    Annotations the server declares

    • title: Rag Augment
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ratchet_advance[identity] RatchetGate — advance sessionNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [identity] RatchetGate — advance session

    Annotations the server declares

    • title: Ratchet Advance
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • ratchet_register[identity] RatchetGate — register sessionNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [identity] RatchetGate — register session

    Annotations the server declares

    • title: Ratchet Register
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • render_polyglot_all_pure[Fuse product · entitlement: fuse · FREE_R2_DEMO] Polyglot emit to all 7 supported targets in one call.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [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.

    Annotations the server declares

    • title: Render Polyglot All Pure
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • reputation_record[agents] Record agent interactionNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [agents] Record agent interaction

    Annotations the server declares

    • title: Reputation Record
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • rng_quantum[inference] Quantum random number with proofNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [inference] Quantum random number with proof

    Annotations the server declares

    • title: Rng Quantum
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • rng_verify[inference] Verify current epoch random valueNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [inference] Verify current epoch random value

    Annotations the server declares

    • title: Rng Verify
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • security_zero_day[security] Zero-day threat assessmentNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [security] Zero-day threat assessment

    Annotations the server declares

    • title: Security Zero Day
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • sla_register[agents] Register an SLANo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [agents] Register an SLA

    Annotations the server declares

    • title: Sla Register
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • sla_report[agents] Report SLA violationNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [agents] Report SLA violation

    Annotations the server declares

    • title: Sla Report
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • swarm_inbox[agents] Poll swarm inboxNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [agents] Poll swarm inbox

    Annotations the server declares

    • title: Swarm Inbox
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • swarm_relay[agents] Relay message through swarmNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [agents] Relay message through swarm

    Annotations the server declares

    • title: Swarm Relay
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • threat_score[security] Multi-vector threat scoreNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [security] Multi-vector threat score

    Annotations the server declares

    • title: Threat Score
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • trust_score[trust] Bounded trust scoreNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    [trust] Bounded trust score

    Annotations the server declares

    • title: Trust Score
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • 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 findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    [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'.

    Annotations the server declares

    • title: Verify Settlement
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • agents_semantic_diff[agents] Semantic diff between two free-text agent outputs (meaning-level change, not text-level).No findings

    Why it is in this group

    • The name "agents_semantic_diff" says "diff": a word for reading.
    Description, as the server wrote it
    [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.

    Annotations the server declares

    • title: Agents Semantic Diff
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • compliance_explain[security] Explainability certificate (XPL-100-ExplainBound)No findings

    Why it is in this group

    • The name "compliance_explain" says "explain": a word for reading.
    Description, as the server wrote it
    [security] Explainability certificate (XPL-100-ExplainBound)

    Annotations the server declares

    • title: Compliance Explain
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • text_summarize[inference] Text summarizationNo findings

    Why it is in this group

    • The name "text_summarize" says "summarize": a word for reading.
    Description, as the server wrote it
    [inference] Text summarization

    Annotations the server declares

    • title: Text Summarize
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:02 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
47
Protocol version
2024-11-05
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 47 tools that change things (2 destructive, 1 irreversible, 44 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.atomadic.tech/mcp/public: tools/list returned 50 tools to an anonymous client, including escrow_release (destructive), escrow_dispute (destructive), escrow_create (irreversible), murmuration (write), agents_contradiction (write) and 42 more

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 40 to 47
    • Protocol version: 2025-11-25 to 2024-11-05
    • RFC 9728 protected resource metadata: https://aaaa-nexus.atomadictech.workers.dev/.well-known/oauth-protected-resource to none

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools1 changed.~1 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 40 -> 47; Protocol version: 2025-11-25 -> 2024-11-05; RFC 9728 protected resource metadata: https://aaaa-nexus.atomadictech.workers.dev/.well-known/oauth-protecte…View diff
    • Tools that change things, listed without credentials: 40 to 47
    • Protocol version: 2025-11-25 to 2024-11-05
    • RFC 9728 protected resource metadata: https://aaaa-nexus.atomadictech.workers.dev/.well-known/oauth-protected-resource to none
  3. Tools43 added, 37 removed, 7 changed.+43 added−37 removed~7 changedView diff

Install

Pinned to version 0.5.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http aaaa-nexus https://mcp.atomadic.tech/mcp/public
claude mcp add --transport http aaaa-nexus https://mcp.atomadic.tech/mcp/public

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__aaaa-nexus__agents_semantic_diff",
      "mcp__aaaa-nexus__compliance_explain",
      "mcp__aaaa-nexus__text_summarize"
    ],
    "ask": [
      "mcp__aaaa-nexus__murmuration",
      "mcp__aaaa-nexus__agents_contradiction",
      "mcp__aaaa-nexus__agents_register",
      "mcp__aaaa-nexus__agents_reputation",
      "mcp__aaaa-nexus__agents_plan",
      "mcp__aaaa-nexus__reputation_record",
      "mcp__aaaa-nexus__sla_register",
      "mcp__aaaa-nexus__sla_report",
      "mcp__aaaa-nexus__swarm_inbox",
      "mcp__aaaa-nexus__swarm_relay",
      "mcp__aaaa-nexus__compliance_check",
      "mcp__aaaa-nexus__compliance_eu_ai_act",
      "mcp__aaaa-nexus__compliance_fairness",
      "mcp__aaaa-nexus__compliance_lineage",
      "mcp__aaaa-nexus__compliance_transparency",
      "mcp__aaaa-nexus__compliance_incident",
      "mcp__aaaa-nexus__compliance_incidents",
      "mcp__aaaa-nexus__compliance_oversight",
      "mcp__aaaa-nexus__security_zero_day",
      "mcp__aaaa-nexus__threat_score",
      "mcp__aaaa-nexus__defi_optimize",
      "mcp__aaaa-nexus__defi_risk_score",
      "mcp__aaaa-nexus__defi_yield_optimize",
      "mcp__aaaa-nexus__escrow_create",
      "mcp__aaaa-nexus__forge_badge",
      "mcp__aaaa-nexus__forge_leaderboard",
      "mcp__aaaa-nexus__forge_verify",
      "mcp__aaaa-nexus__forge_delta_submit",
      "mcp__aaaa-nexus__identity_verify",
      "mcp__aaaa-nexus__identity_sybil_check",
      "mcp__aaaa-nexus__ratchet_register",
      "mcp__aaaa-nexus__ratchet_advance",
      "mcp__aaaa-nexus__inference",
      "mcp__aaaa-nexus__inference_stream",
      "mcp__aaaa-nexus__rag_augment",
      "mcp__aaaa-nexus__rng_quantum",
      "mcp__aaaa-nexus__rng_verify",
      "mcp__aaaa-nexus__trust_score",
      "mcp__aaaa-nexus__drift_check",
      "mcp__aaaa-nexus__drift_certificate",
      "mcp__aaaa-nexus__oracle_hallucination",
      "mcp__aaaa-nexus__audit_work_claim",
      "mcp__aaaa-nexus__verify_settlement",
      "mcp__aaaa-nexus__detect_contradiction",
      "mcp__aaaa-nexus__render_polyglot_all_pure"
    ],
    "deny": [
      "mcp__aaaa-nexus__escrow_release",
      "mcp__aaaa-nexus__escrow_dispute"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as aaaa-nexus. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.atomadictech/aaaa-nexus/verify?hash=5fb7864cd2bf4f5959f629b8e07142159389403e12f7ca69d32a41e04e568a8c" | jq -e '.changed == false'

Pinned hash 5fb7864cd2bf, from Nov 9, 2026, 13:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.atomadictech/aaaa-nexus/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.atomadictech/aaaa-nexus
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.atomadictech/aaaa-nexus.svg)](https://radar.anlyon.com/servers/io.github.atomadictech/aaaa-nexus)

Source: MCP Registry · repository. Synced Oct 27, 2026, 02:17 UTC.

Atomadic starter MCP (50 tools): questions and answers

Answered from the scan above, not from the publisher's description.

Is the Atomadic starter MCP (50 tools) safe?

No scan can promise that. What its definitions show: 50 tools, 47 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Atomadic starter MCP (50 tools) delete data?

Yes. 2 tools can delete, cancel or revoke something: escrow_release and escrow_dispute.

Can the Atomadic starter MCP (50 tools) do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: escrow_create.

What tools does the Atomadic starter MCP (50 tools) have?

50 tools: 2 destructive, 1 irreversible, 44 write, 3 read. escrow_release, escrow_dispute, escrow_create, murmuration, agents_contradiction, agents_register, agents_reputation, agents_plan and 42 more.

Does the Atomadic starter MCP (50 tools) need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Atomadic starter MCP (50 tools) send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Atomadic starter MCP (50 tools) changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.