Atomadic MCP
REMOTE · MCP.ATOMADIC.TECH
Atomadic MCP: 68 deterministic tools for agent identity, escrow, SLA, EU AI Act compliance.
Available components
Last scanned (5 hours ago)
Scores higher than 44% of remote servers
Reachable. Last reached 5 Nov 2026.
Category AI and Machine Learning
Recent critical change
Authorization (27 Oct 2026). See the changelog before you install this server.
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. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (escrow_dispute). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability49
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 3129 tokens (~46/item across 68 items; 68 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management61
- Stability check failed: schema churn in the 19 days we've observed: 1 tool removals, 1 breaking changes, 0 auth/transport breaks, 1 additions. See how to fix → Fail
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 13% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 68 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 69 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 58 to 61.
- 4 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “compliance_check” rewrote its description, which is the text the model reads security
- “compliance_check” dropped the required parameter “data_type” ▼ functional
- “compliance_check” dropped the required parameter “jurisdiction” ▼ functional
- “compliance_check” dropped the required parameter “operation” ▼ functional
- Schema quality: poor → fair functional
- Server version: 124 → 126 functional
- “compliance_check” added an optional parameter “chain_depth” cosmetic
- “compliance_check” added an optional parameter “description” cosmetic
- “compliance_check” added an optional parameter “kl_divergence” cosmetic
- 3 Nov 26 +1
- Server version: 0.6.9 → 124 functional
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 45 to 48.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 38 to 42.
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 32 to 35.
- 27 Oct 26 0
- Authorization: unverified → fail ▼ critical
- Stability: 0.30 → fail ▼ security
- A breaking change shipped without a version bump: still 0.6.9 ▼ security
- Tool “forge_badge_{model}” was removed ▼ security
- Tool “agents_contradiction” rewrote its description, which is the text the model reads security
- Tool “agents_semantic_diff” rewrote its description, which is the text the model reads security
- Tool “detect_contradiction” rewrote its description, which is the text the model reads security
- Tool “escrow_dispute” is now declared destructive security
- Tool “escrow_release” is now declared destructive security
- Tool “forge_quarantine” is now declared destructive security
- New tool “forge_badge” functional
- Tool “agents_contradiction” changed its title: Agents Contradiction cosmetic
- Tool “agents_intent_classify” changed its title: Agents Intent Classify cosmetic
- Tool “agents_plan” changed its title: Agents Plan cosmetic
- Tool “agents_register” changed its title: Agents Register cosmetic
- Tool “agents_reputation” changed its title: Agents Reputation cosmetic
- Tool “agents_semantic_diff” changed its title: Agents Semantic Diff cosmetic
- Tool “agents_topology” changed its title: Agents Topology cosmetic
- Tool “audit_work_claim” changed its title: Audit Work Claim cosmetic
- Tool “compliance_check” changed its title: Compliance Check cosmetic
- Tool “compliance_eu_ai_act” changed its title: Compliance Eu Ai Act cosmetic
- Tool “compliance_explain” changed its title: Compliance Explain cosmetic
- Tool “compliance_fairness” changed its title: Compliance Fairness cosmetic
- Tool “compliance_incident” changed its title: Compliance Incident cosmetic
- Tool “compliance_incidents” changed its title: Compliance Incidents cosmetic
- Tool “compliance_lineage” changed its title: Compliance Lineage cosmetic
- Tool “compliance_oversight” changed its title: Compliance Oversight cosmetic
- Tool “compliance_oversight_history” changed its title: Compliance Oversight History cosmetic
- Tool “compliance_transparency” changed its title: Compliance Transparency cosmetic
- Tool “defi_bridge_verify” changed its title: Defi Bridge Verify cosmetic
- Tool “defi_contract_audit” changed its title: Defi Contract Audit cosmetic
- Tool “defi_liquidation_check” changed its title: Defi Liquidation Check cosmetic
- Tool “defi_optimize” changed its title: Defi Optimize cosmetic
- Tool “defi_oracle_verify” changed its title: Defi Oracle Verify cosmetic
- Tool “defi_risk_score” changed its title: Defi Risk Score cosmetic
- Tool “defi_yield_optimize” changed its title: Defi Yield Optimize cosmetic
- Tool “detect_contradiction” changed its title: Detect Contradiction cosmetic
- Tool “drift_certificate” changed its title: Drift Certificate cosmetic
- Tool “drift_check” changed its title: Drift Check cosmetic
- Tool “enforce_sla” changed its title: Enforce Sla cosmetic
- Tool “escrow_create” changed its title: Escrow Create cosmetic
- Tool “escrow_dispute” changed its title: Escrow Dispute cosmetic
- Tool “escrow_release” changed its title: Escrow Release cosmetic
- Tool “forge_delta_submit” changed its title: Forge Delta Submit cosmetic
- Tool “forge_leaderboard” changed its title: Forge Leaderboard cosmetic
- Tool “forge_quarantine” changed its title: Forge Quarantine cosmetic
- Tool “forge_verify” changed its title: Forge Verify cosmetic
- Tool “identity_sybil_check” changed its title: Identity Sybil Check cosmetic
- Tool “identity_verify” changed its title: Identity Verify cosmetic
- Tool “inference” changed its title: Inference cosmetic
- Tool “inference_stream” changed its title: Inference Stream cosmetic
- Tool “murmuration” changed its title: Murmuration cosmetic
- Tool “oracle_entropy” changed its title: Oracle Entropy cosmetic
- Tool “oracle_hallucination” changed its title: Oracle Hallucination cosmetic
- Tool “rag_augment” changed its title: Rag Augment cosmetic
- Tool “ratchet_advance” changed its title: Ratchet Advance cosmetic
- Tool “ratchet_probe” changed its title: Ratchet Probe cosmetic
- Tool “ratchet_register” changed its title: Ratchet Register cosmetic
- Tool “receipt_reputation” changed its title: Receipt Reputation cosmetic
- Tool “render_polyglot_all_pure” changed its title: Render Polyglot All Pure cosmetic
- Tool “render_polyglot_roundtrip_pure” changed its title: Render Polyglot Roundtrip Pure cosmetic
- Tool “reputation_record” changed its title: Reputation Record cosmetic
- Tool “rng_quantum” changed its title: Rng Quantum cosmetic
- Tool “rng_verify” changed its title: Rng Verify cosmetic
- Tool “route_capability” changed its title: Route Capability cosmetic
- Tool “security_zero_day” changed its title: Security Zero Day cosmetic
- Tool “sla_register” changed its title: Sla Register cosmetic
- Tool “sla_report” changed its title: Sla Report cosmetic
- Tool “swarm_inbox” changed its title: Swarm Inbox cosmetic
- Tool “swarm_relay” changed its title: Swarm Relay cosmetic
- Tool “text_keywords” changed its title: Text Keywords cosmetic
- Tool “text_sentiment” changed its title: Text Sentiment cosmetic
- Tool “text_summarize” changed its title: Text Summarize cosmetic
- Tool “threat_score” changed its title: Threat Score cosmetic
- Tool “trust_decay” changed its title: Trust Decay cosmetic
- Tool “trust_history” changed its title: Trust History cosmetic
- Tool “trust_score” changed its title: Trust Score cosmetic
- Tool “verify_settlement” changed its title: Verify Settlement cosmetic
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://mcp.atomadic.tech/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=atomadic.tech | CN=WE1,O=Google Trust Services,C=US | 3 Oct 2026 | 1 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 897545e9c60854421346cc39e45cdd63 |
| SANs: atomadic.tech, mcp.atomadic.tech, *.mcp.atomadic.tech | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.atomadic.tech. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| tech. | present | 2185 | 13 | Verified |
| atomadic.tech. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.atomadic.tech/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.atomadic.tech/mcp | HTTPS enforced | 301 | https://mcp.atomadic.tech/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
render_polyglot_roundtrip_pure Render Polyglot Roundtrip Pure ~98
[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.
| Name | Type | Req | Description |
|---|---|---|---|
| atom_name | string | yes | – |
| language | string | – | – |
| source_text | string | yes | – |
No output schema declared.
No examples provided.
reputation_record Reputation Record ~47
[agents] Record agent interaction
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| counterparty_id | string | – | – |
| interaction_type | string | yes | – |
| outcome | string | yes | – |
No output schema declared.
No examples provided.
rng_quantum Rng Quantum ~19
[inference] Quantum random number with proof
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
rng_verify Rng Verify ~18
[inference] Verify current epoch random value
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
route_capability Route Capability ~54
[Ledger product, entitlement: ledger] Route a natural-language intent to a deterministic capability/pipeline coordinate. 3 free calls/day, then entitlement 'ledger'.
| Name | Type | Req | Description |
|---|---|---|---|
| intent | string | yes | The natural-language intent to route. |
No output schema declared.
No examples provided.
security_zero_day Security Zero Day ~31
[security] Zero-day threat assessment
| Name | Type | Req | Description |
|---|---|---|---|
| context | object | – | – |
| target | string | yes | – |
No output schema declared.
No examples provided.
sla_register Sla Register ~38
[agents] Register an SLA
| Name | Type | Req | Description |
|---|---|---|---|
| consumer_id | string | yes | – |
| provider_id | string | yes | – |
| terms | object | yes | – |
No output schema declared.
No examples provided.
sla_report Sla Report ~38
[agents] Report SLA violation
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | – |
| sla_id | string | yes | – |
| violation_type | string | yes | – |
No output schema declared.
No examples provided.
swarm_inbox Swarm Inbox ~16
[agents] Poll swarm inbox
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
swarm_relay Swarm Relay ~44
[agents] Relay message through swarm
| Name | Type | Req | Description |
|---|---|---|---|
| message | object | yes | – |
| target_agent_id | string | yes | – |
| ttl | integer | – | Hop limit for relay |
No output schema declared.
No examples provided.
text_keywords Text Keywords ~30
[inference] Keyword extraction
| Name | Type | Req | Description |
|---|---|---|---|
| max_keywords | integer | – | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
text_sentiment Text Sentiment ~24
[inference] Sentiment analysis
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | – |
No output schema declared.
No examples provided.
text_summarize Text Summarize ~25
[inference] Text summarization
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | – |
No output schema declared.
No examples provided.
threat_score Threat Score ~31
[security] Multi-vector threat score
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| context | string | – | – |
No output schema declared.
No examples provided.
trust_decay Trust Decay ~16
[trust] Current trust ceiling value
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
trust_history Trust History ~23
[trust] Trust score history
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
No output schema declared.
No examples provided.
trust_score Trust Score ~24
[trust] Bounded trust score
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
No output schema declared.
No examples provided.
verify_settlement Verify Settlement ~85
[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'.
| Name | Type | Req | Description |
|---|---|---|---|
| claimed_digest | string | – | Claimed digest the payout is conditioned on. |
| inputs | object | yes | The work payload backing the settlement. |
No output schema declared.
No examples provided.
How do I install the Atomadic MCP server?
Atomadic MCP is a hosted endpoint at https://mcp.atomadic.tech/mcp, 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.
remote · mcp.atomadic.tech
claude mcp add --transport http tech-atomadic-atomadic 'https://mcp.atomadic.tech/mcp'
What is the Atomadic MCP server?
Atomadic MCP is listed in the public MCP registry as tech.atomadic/atomadic. Atomadic MCP: 68 deterministic tools for agent identity, escrow, SLA, EU AI Act compliance. This page covers its hosted endpoint (https://mcp.atomadic.tech/mcp).
Is the Atomadic MCP server safe to use?
Atomadic MCP scores 63 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 MCP server expose?
Atomadic MCP exposes 68 tools: murmuration, agents_contradiction, agents_intent_classify, agents_plan, agents_register, and 63 more. Their descriptions and schemas cost roughly 2,952 tokens of context every time the server is loaded.
Does the Atomadic MCP server require authentication?
No. We connected to Atomadic MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Atomadic MCP server still maintained?
Atomadic MCP 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.