Homo Universalis — HU-DIAMOND v1.1 Cryptographic Verifier & AST Kintsugi MCP Server
Working · 31 ms Security Aai.homouniversalis/cryptography-merkle-tree-rfc6962-jws-ed25519-es256-zero-knowledge-python-ast-code-audit-formal-verification-mutation-testing-reed-muller-multi-agent-deep-think-crucible-barycenterv1.5.2 Domain verified
Zero-auth Cryptographic Notary & AST Verifier: Reed-Muller RM(1,3), L1..L7, RFC 6962 & ES256 JWS.
Maintained by@Cheliot(verified)Also a maintainer?
Try it
Call this server's tools from your browser. Nothing to install.
https://homouniversalis.ai/mcp/diamond?pillar=cryptography-ast
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
simulate_diamond_spiral_budget Read-only
Compute deterministic LLM call counts, token budgets, and EUR/Seed costs for 1 to 4 spiral turns of the 8-vertex Diamond Wheel multi-agent orchestrator. Use this tool only to estimate call volume and cost before launching a multi-agent run, or use `verify_diamond_crucible_and_ast` to audit Python code and RM(1,3) proofs, and `verify_sovereign_shield_merkle` to notarize text in an RFC 6962 Merkle tree. Zero-auth, stateless, and free (0.00 EUR), executing pure arithmetic without invoking any LLM. Each spiral turn (`rounds` `1..4`) adds 9 LLM calls (4 creators, 4 antipodal auditors, and 1 barycenter synthesizer, totaling `9, 18, 27, or 36` calls, plus 10 final inquisition calls when `rounds=4`), while `tier='supreme'` prices calls for `gemini-4-argon` (`10,000` to `64,000` Seeds / `10.00` to `64.00 EUR`) and `tier='flash'` prices calls for `gemini-3.8-flash` at reduced cost, and `lang` localizes vertex role descriptions.
Output language for localized vertex and budget breakdowns ('en' English, 'es' Spanish, or 'ca' Catalan).
Model pricing tier ('supreme' for gemini-4-argon Deep Think or 'flash' for high-speed gemini-3.8-flash).
Number of spiral turns (`1..4`, corresponding to `9, 18, 27, or 36` spiral calls plus the 10-call Supreme Inquisition dome on round 4).
Install
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http cryptography-merkle-tree-rfc6962-jws-ed25519-es256-zero-knowledge-python-ast-code-audit-formal-verification-mutation-testing-reed-muller-multi-agent-deep-think-crucible-barycenter 'https://homouniversalis.ai/mcp/diamond?pillar=cryptography-ast'
Tools (3)
Tool list last changed Nov 9, 2026.
simulate_diamond_spiral_budgetCompute deterministic LLM call counts, token budgets, and EUR/Seed costs for 1 to 4 spiral turns of the 8-vertex Diamond Wheel multi-agent orchestrator. Use this tool only to estimate call volume and cost before launching a multi-agent run, or use `verify_diamond_crucible_and_ast` to audit Python code and RM(1,3) proofs, and `verify_sovereign_shield_merkle` to notarize text in an RFC 6962 Merkle tree. Zero-auth, stateless, and free (0.00 EUR), executing pure arithmetic without invoking any LLM. Each spiral turn (`rounds` `1..4`) adds 9 LLM calls (4 creators, 4 antipodal auditors, and 1 barycenter synthesizer, totaling `9, 18, 27, or 36` calls, plus 10 final inquisition calls when `rounds=4`), while `tier='supreme'` prices calls for `gemini-4-argon` (`10,000` to `64,000` Seeds / `10.00` to `64.00 EUR`) and `tier='flash'` prices calls for `gemini-3.8-flash` at reduced cost, and `lang` localizes vertex role descriptions.
read-only
simulate_diamond_spiral_budget
Compute deterministic LLM call counts, token budgets, and EUR/Seed costs for 1 to 4 spiral turns of the 8-vertex Diamond Wheel multi-agent orchestrator. Use this tool only to estimate call volume and cost before launching a multi-agent run, or use `verify_diamond_crucible_and_ast` to audit Python code and RM(1,3) proofs, and `verify_sovereign_shield_merkle` to notarize text in an RFC 6962 Merkle tree. Zero-auth, stateless, and free (0.00 EUR), executing pure arithmetic without invoking any LLM. Each spiral turn (`rounds` `1..4`) adds 9 LLM calls (4 creators, 4 antipodal auditors, and 1 barycenter synthesizer, totaling `9, 18, 27, or 36` calls, plus 10 final inquisition calls when `rounds=4`), while `tier='supreme'` prices calls for `gemini-4-argon` (`10,000` to `64,000` Seeds / `10.00` to `64.00 EUR`) and `tier='flash'` prices calls for `gemini-3.8-flash` at reduced cost, and `lang` localizes vertex role descriptions.
| Argument | Type | Description |
|---|---|---|
| lang | string | Output language for localized vertex and budget breakdowns ('en' English, 'es' Spanish, or 'ca' Catalan). |
| tier | string | Model pricing tier ('supreme' for gemini-4-argon Deep Think or 'flash' for high-speed gemini-3.8-flash). |
| rounds | integer | Number of spiral turns (`1..4`, corresponding to `9, 18, 27, or 36` spiral calls plus the 10-call Supreme Inquisition dome on round 4). |
Input schema (JSON)
{
"type": "object",
"properties": {
"lang": {
"enum": [
"en",
"es",
"ca"
],
"type": "string",
"default": "en",
"description": "Output language for localized vertex and budget breakdowns ('en' English, 'es' Spanish, or 'ca' Catalan)."
},
"tier": {
"enum": [
"supreme",
"flash"
],
"type": "string",
"default": "supreme",
"description": "Model pricing tier ('supreme' for gemini-4-argon Deep Think or 'flash' for high-speed gemini-3.8-flash)."
},
"rounds": {
"type": "integer",
"default": 1,
"maximum": 4,
"minimum": 1,
"description": "Number of spiral turns (`1..4`, corresponding to `9, 18, 27, or 36` spiral calls plus the 10-call Supreme Inquisition dome on round 4)."
}
}
}verify_diamond_crucible_and_astAudit Python source code and verify the 8-vertex Reed-Muller RM(1,3) cryptographic crucible in under 4 ms. Use this tool when auditing Python code snippets (`code_markdown`) or obtaining an ES256-signed crucible attestation, or use `verify_sovereign_shield_merkle` for RFC 6962 Merkle tree notarization and PII purification, and `simulate_diamond_spiral_budget` for multi-agent call and cost estimation. Zero-auth, stateless, and free (0.00 EUR), running four checks on every call: RM(1,3) antipodal geometry across 256 states in Q^3, non-coercion laws L1..L7 (`c_levels == 1`), 22/22 killed policy mutants, and Python AST static verification (syntax, import-hoist guard, and zero placeholders) whenever `code_markdown` is provided. Setting `diag_active` (`1..4`) selects which body diagonal pair receives double weight in the rational barycenter calculation, `lang` localizes diagnostic summaries, and any Python syntax error or AST rule violation sets `status` to `'violation_detected'` with line-level diagnostics while still returning a valid RFC 8785 (JCS) + RFC 7515 (JWS ES256) signature.
read-only
verify_diamond_crucible_and_ast
Audit Python source code and verify the 8-vertex Reed-Muller RM(1,3) cryptographic crucible in under 4 ms. Use this tool when auditing Python code snippets (`code_markdown`) or obtaining an ES256-signed crucible attestation, or use `verify_sovereign_shield_merkle` for RFC 6962 Merkle tree notarization and PII purification, and `simulate_diamond_spiral_budget` for multi-agent call and cost estimation. Zero-auth, stateless, and free (0.00 EUR), running four checks on every call: RM(1,3) antipodal geometry across 256 states in Q^3, non-coercion laws L1..L7 (`c_levels == 1`), 22/22 killed policy mutants, and Python AST static verification (syntax, import-hoist guard, and zero placeholders) whenever `code_markdown` is provided. Setting `diag_active` (`1..4`) selects which body diagonal pair receives double weight in the rational barycenter calculation, `lang` localizes diagnostic summaries, and any Python syntax error or AST rule violation sets `status` to `'violation_detected'` with line-level diagnostics while still returning a valid RFC 8785 (JCS) + RFC 7515 (JWS ES256) signature.
| Argument | Type | Description |
|---|---|---|
| lang | string | Output language for localized verification summaries ('en' English, 'es' Spanish, or 'ca' Catalan). |
| diag_active | integer | Active body diagonal of the 8-vertex Stella Octangula (`1` Fire, `2` Earth, `3` Air, or `4` Water; default `2`), assigning weight 2 to the active antipodal pair in the rational barycenter. |
| code_markdown | string | Optional Python source code or Markdown containing ```python blocks to audit with the AST Kintsugi Verifier (Syntax, Rule 4 Import Hoist Guard, and Rule 7 Zero Placeholders). When omitted, only the 256-state RM(1,3) crucible and 22/22 mutant checks run. |
Input schema (JSON)
{
"type": "object",
"properties": {
"lang": {
"enum": [
"en",
"es",
"ca"
],
"type": "string",
"default": "en",
"description": "Output language for localized verification summaries ('en' English, 'es' Spanish, or 'ca' Catalan)."
},
"diag_active": {
"type": "integer",
"default": 2,
"maximum": 4,
"minimum": 1,
"description": "Active body diagonal of the 8-vertex Stella Octangula (`1` Fire, `2` Earth, `3` Air, or `4` Water; default `2`), assigning weight 2 to the active antipodal pair in the rational barycenter."
},
"code_markdown": {
"type": "string",
"description": "Optional Python source code or Markdown containing ```python blocks to audit with the AST Kintsugi Verifier (Syntax, Rule 4 Import Hoist Guard, and Rule 7 Zero Placeholders). When omitted, only the 256-state RM(1,3) crucible and 22/22 mutant checks run."
}
}
}verify_sovereign_shield_merkleNotarize text into an RFC 6962 binary Merkle audit tree, strip PII under Zero-Knowledge privacy rules, and verify cognitive load limits in under 1 ms. Use this tool when notarizing text, purifying PII, or auditing cognitive load and fair-share economics, or use `verify_diamond_crucible_and_ast` for Python AST code auditing and RM(1,3) proofs, and `simulate_diamond_spiral_budget` for multi-agent call and cost estimation. Zero-auth, stateless, and free (0.00 EUR), always executing all four verification pillars: RFC 6962 domain-separated Merkle inclusion and consistency proofs, Zero-Knowledge PII purification with a flat `c_levels == 1` receipt, cognitive sovereignty laws L1..L7 checking that load `L` stays within `budget_b` and `cost_zero_stop` is true, and exact rational fair-share allocation (`50%` compute, `25%` platform, `25%` community scholarship). Passing PII in `text` redacts sensitive tokens before Merkle hashing, setting `cost_zero_stop=false` or `budget_b < 120` triggers a law violation flag in `pillar_iii_cognitive_sovereignty_laws_L1_to_L7`, and `lang` localizes all pillar reports.
read-only
verify_sovereign_shield_merkle
Notarize text into an RFC 6962 binary Merkle audit tree, strip PII under Zero-Knowledge privacy rules, and verify cognitive load limits in under 1 ms. Use this tool when notarizing text, purifying PII, or auditing cognitive load and fair-share economics, or use `verify_diamond_crucible_and_ast` for Python AST code auditing and RM(1,3) proofs, and `simulate_diamond_spiral_budget` for multi-agent call and cost estimation. Zero-auth, stateless, and free (0.00 EUR), always executing all four verification pillars: RFC 6962 domain-separated Merkle inclusion and consistency proofs, Zero-Knowledge PII purification with a flat `c_levels == 1` receipt, cognitive sovereignty laws L1..L7 checking that load `L` stays within `budget_b` and `cost_zero_stop` is true, and exact rational fair-share allocation (`50%` compute, `25%` platform, `25%` community scholarship). Passing PII in `text` redacts sensitive tokens before Merkle hashing, setting `cost_zero_stop=false` or `budget_b < 120` triggers a law violation flag in `pillar_iii_cognitive_sovereignty_laws_L1_to_L7`, and `lang` localizes all pillar reports.
| Argument | Type | Description |
|---|---|---|
| lang | string | Output language for localized notary and compliance reports ('en' English, 'es' Spanish, or 'ca' Catalan). |
| text | string | Optional text message to scrub for PII (emails, phones, coordinates, ISO birth dates) and anchor as a domain-separated `0x00` leaf in the RFC 6962 Merkle audit tree. |
| budget_b | integer | Maximum allowed cognitive load budget `B` (`1..10000`, default `250`) evaluated against current load `L` (`0 <= L <= B`). |
| cost_zero_stop | boolean | Whether user pause or exit carries zero penalty (`true` satisfies Law L2; `false` triggers an anti-coercion violation). |
Input schema (JSON)
{
"type": "object",
"properties": {
"lang": {
"enum": [
"en",
"es",
"ca"
],
"type": "string",
"default": "en",
"description": "Output language for localized notary and compliance reports ('en' English, 'es' Spanish, or 'ca' Catalan)."
},
"text": {
"type": "string",
"description": "Optional text message to scrub for PII (emails, phones, coordinates, ISO birth dates) and anchor as a domain-separated `0x00` leaf in the RFC 6962 Merkle audit tree."
},
"budget_b": {
"type": "integer",
"default": 250,
"maximum": 10000,
"minimum": 1,
"description": "Maximum allowed cognitive load budget `B` (`1..10000`, default `250`) evaluated against current load `L` (`0 <= L <= B`)."
},
"cost_zero_stop": {
"type": "boolean",
"default": true,
"description": "Whether user pause or exit carries zero penalty (`true` satisfies Law L2; `false` triggers an anti-coercion violation)."
}
}
}Security checkA100/100
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 9, 2026.
- Hidden or reordered text
- Overriding the model's instructions
- Hiding actions from the user
- Reading keys or credentials
- Fake system tags
- Steering other servers' tools
- Pulling in the conversation
- Smuggling parameters
- Demanding to be used for everything
- Steering away from web search
- Download-and-run commands
- Encoded blobs
- Invisible characters
- Credentials as tool arguments
- Very long descriptions
- Read and write hints
Tool changes
What changed in this server's tools since we started watching, newest first. Each change is scanned again.
simulate_diamond_spiral_budgetchanged (description, inputs, hints)Nov 9, 2026
Zero-costCompute(`0.00deterministicEUR`)LLMdeterministiccallbudgetcounts,simulatortoken budgets, and EUR/Seed costs for 1 to 4 spiral turns of the8-Vertex8-vertex Diamond Wheelinmulti-agentDeeporchestrator.ThinkUse(`gemini-4-argon`),thiscomputingtool only to estimate callcountsvolume andSeedscostofbeforeLightlaunchingfora1multi-agent run, or use `verify_diamond_crucible_and_ast` to audit Python code and RM(1,3) proofs, and `verify_sovereign_shield_merkle` to notarize text in an RFC 6962 Merkle tree. Zero-auth, stateless, and free (0.00 EUR), executing pure arithmetic without invoking any LLM. Each spiral turn (`rounds` `1..4`) adds 9 LLM calls (4 creators, 4SpiralantipodalTurnsauditors,(`9,and 1 barycenter synthesizer, totaling `9, 18, 27, or 36`Deepcalls,Thinkplus 10 final inquisition calls+when`6+4`rounds=4`),=while10``tier='supreme'`immortalprices calls for `gemini-4-argon` (`10,000` to `64,000` Seeds / `10.00` to `64.00 EUR`) and `tier='flash'` prices calls for `gemini-3.8-flash` at reduced cost, and `lang` localizes vertexshield).role descriptions.{ "type": "object", "properties": { "lang": { "enum": [ "ca", "es", "en" ], "type": "string", "default": "en", "description": "Output language code ('ca', 'es', or 'en')." }, "tier": { "enum": [ "supreme", "flash" ], "type": "string", "default": "supreme", "description": "Engine tier ('supreme' for gemini-4-argon or 'flash' for gemini-3.8-flash)." }, "rounds": { "type": "integer", "default": 1, "maximum": 4, "minimum": 1, "description": "Number of spiral turns (`1..4`, corresponding to `9, 18, 27, 36` Deep Think calls)." } } }{ "type": "object", "properties": { "lang": { "enum": [ "en", "es", "ca" ], "type": "string", "default": "en", "description": "Output language for localized vertex and budget breakdowns ('en' English, 'es' Spanish, or 'ca' Catalan)." }, "tier": { "enum": [ "supreme", "flash" ], "type": "string", "default": "supreme", "description": "Model pricing tier ('supreme' for gemini-4-argon Deep Think or 'flash' for high-speed gemini-3.8-flash)." }, "rounds": { "type": "integer", "default": 1, "maximum": 4, "minimum": 1, "description": "Number of spiral turns (`1..4`, corresponding to `9, 18, 27, or 36` spiral calls plus the 10-call Supreme Inquisition dome on round 4)." } } }verify_sovereign_shield_merklechanged (description, inputs, hints)Nov 9, 2026
ExecuteNotarizethetext4-PillarintoHU-SOVEREIGN-BEACONanv1.0RFCPublic6962NotarybinaryverificationMerkle(<audit tree, strip PII under Zero-Knowledge privacy rules, and verify cognitive load limits in under 1ms,ms.Zero-Auth,Use0.00thisEUR):tool(1)whenRFCnotarizing6962text,Domain-SeparatedpurifyingBinaryPII,MerkleorAuditauditingTreecognitive(`0x00`loadleaf,and`0x01`fair-shareinternaleconomics,node),or(2)useRule`verify_diamond_crucible_and_ast`14forThree-RingPython AST code auditing and RM(1,3) proofs, and `simulate_diamond_spiral_budget` for multi-agent call and cost estimation. Zero-auth, stateless, and free (0.00 EUR), always executing all four verification pillars: RFC 6962 domain-separated Merkle inclusion and consistency proofs, Zero-KnowledgePurifierPII&purification`SovereignDignityReceipt`with(`c_levelsa==flat1`),`c_levels(3)==Cognitive1`Sovereigntyreceipt,&cognitiveAnti-CoercionsovereigntyVerifierlaws(`LawsL1..L7L1..L7`,checkingEUthatAIloadAct`L`Art.stays50within&`budget_b`CaliforniaandSB`cost_zero_stop`243isalignment),true, and(4)exactPersephonerational&fair-shareDemeterallocationExact(`50%`Rationalcompute,Fair-Share`25%`Solverplatform,(`fractions.Fraction`).`25%` community scholarship). Passing PII in `text` redacts sensitive tokens before Merkle hashing, setting `cost_zero_stop=false` or `budget_b < 120` triggers a law violation flag in `pillar_iii_cognitive_sovereignty_laws_L1_to_L7`, and `lang` localizes all pillar reports.{ "type": "object", "properties": { "lang": { "enum": [ "es", "en", "ca" ], "type": "string", "default": "en", "description": "Output language code ('es', 'en', or 'ca')." }, "text": { "type": "string", "description": "Optional text to purify under Rule 14 Three-Ring Zero-Knowledge Privacy and anchor in the RFC 6962 Merkle tree." }, "budget_B": { "type": "integer", "default": 250, "description": "Maximum allowed cognitive load budget `B` (`0 <= L <= B`)." }, "cost_zero_stop": { "type": "boolean", "default": true, "description": "Whether pause/exit carries zero penalty (`L2`)." } } }{ "type": "object", "properties": { "lang": { "enum": [ "en", "es", "ca" ], "type": "string", "default": "en", "description": "Output language for localized notary and compliance reports ('en' English, 'es' Spanish, or 'ca' Catalan)." }, "text": { "type": "string", "description": "Optional text message to scrub for PII (emails, phones, coordinates, ISO birth dates) and anchor as a domain-separated `0x00` leaf in the RFC 6962 Merkle audit tree." }, "budget_b": { "type": "integer", "default": 250, "maximum": 10000, "minimum": 1, "description": "Maximum allowed cognitive load budget `B` (`1..10000`, default `250`) evaluated against current load `L` (`0 <= L <= B`)." }, "cost_zero_stop": { "type": "boolean", "default": true, "description": "Whether user pause or exit carries zero penalty (`true` satisfies Law L2; `false` triggers an anti-coercion violation)." } } }verify_diamond_crucible_and_astchanged (description, inputs)Nov 9, 2026
ExecuteAudit Python source code and verify theHU-DIAMOND-CRUCIBLE8-vertexv1.1Reed-MullerliveRM(1,3) cryptographic crucible in under 4 ms. Use this tool when auditing Python code snippets (`code_markdown`) or obtaining an ES256-signed crucible attestation, or use `verify_sovereign_shield_merkle` for RFC 6962 Merkle tree notarization andstaticPIIASTpurification,verificationand(<`simulate_diamond_spiral_budget`4forms,multi-agentZero-Auth,call0.00andEUR).costVerifiesestimation.(1)Zero-auth,Reed-Mullerstateless,RM(1,3)and=free[8,4,4]_2(0.00antipodalEUR),geometryrunningacrossfourallchecks256onstateseveryincall:Q^3RM(1,3)(d_minantipodal=geometry4),across(2)256HU-DIAMOND/v1statesFilind'OrQ^3, non-coercion laws L1..L7 (`c_levels ==1`,1`),lexicographical22/22commitkilledsorting),policy(3)mutants,22/22andadversarialPythonpolicy-switchASTmutantsstatickilledverification(M01..M22),(syntax, import-hoist guard, and(4)zeroPythonplaceholders)ASTwheneverKintsugi`code_markdown`staticisverificationprovided.(`RuleSetting4``diag_active`Import(`1..4`)HoistselectsGuardwhich+body`Rulediagonal7`pairZeroreceivesPlaceholders)doubleonweight in the rational barycenter calculation, `lang` localizes diagnostic summaries, and any`code_markdown`,Python syntax error or AST rule violation sets `status` to `'violation_detected'` with line-level diagnostics while still returningana valid RFC 8785 (JCS) + RFC 7515 (JWS ES256)+RFC6979deterministicsignatureverifiableagainst/.well-known/jwks.json.signature.{ "type": "object", "properties": { "lang": { "enum": [ "en", "es", "ca" ], "type": "string", "default": "en", "description": "Output language code ('en', 'es', or 'ca')." }, "diag_active": { "type": "integer", "default": 2, "maximum": 4, "minimum": 1, "description": "Active body diagonal of the Stella Octangula (`1..4`, default `2`)." }, "code_markdown": { "type": "string", "description": "Optional Python source code or Markdown containing ```python blocks to audit with the AST Kintsugi Verifier (Syntax, Rule 4 Import Hoist Guard, Rule 7 Zero Placeholders)." } } }{ "type": "object", "properties": { "lang": { "enum": [ "en", "es", "ca" ], "type": "string", "default": "en", "description": "Output language for localized verification summaries ('en' English, 'es' Spanish, or 'ca' Catalan)." }, "diag_active": { "type": "integer", "default": 2, "maximum": 4, "minimum": 1, "description": "Active body diagonal of the 8-vertex Stella Octangula (`1` Fire, `2` Earth, `3` Air, or `4` Water; default `2`), assigning weight 2 to the active antipodal pair in the rational barycenter." }, "code_markdown": { "type": "string", "description": "Optional Python source code or Markdown containing ```python blocks to audit with the AST Kintsugi Verifier (Syntax, Rule 4 Import Hoist Guard, and Rule 7 Zero Placeholders). When omitted, only the 256-state RM(1,3) crucible and 22/22 mutant checks run." } } }