solmachina-x402

solmachina_decision

SolMachina Decision — the decision layer for autonomous agents: composes on-chain risk signals into ONE answer — EXECUTE / REVIEW / REJECT + SMRI (SolMachina Machine Risk Index 0-100) + confidence + full evidence. A transparent RISK GATE against stated thresholds — NOT financial advice, NOT a profit prediction; returns REVIEW/unknown instead of guessing. Requires ?mint=; optional ?action=, ?amountUsd=, and a named firewall ?policy= (conservative|bluechip|anti-rug|degen).

Input Schema

TableJSON Schema

Name	Required	Description
`tx`	No	Optional base64 serialized transaction to BIND the signed authorization to: the response's authorization.subject.boundTxSha256 = sha256(tx), so your executor honors it only for that exact transaction (Proof-of-Decision per-tx). Also decoded OFFLINE to cross-check that the tx actually references the guarded mint — authorization.subject.txReferencesGuardedMint = true \| false \| "unknown".
`mint`	Yes	Base58 SPL token mint to assess, e.g. DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263 (BONK).
`action`	No	Single nonblank context string; default assess. Does not execute an action.
`policy`	No	Named firewall preset: conservative \| bluechip \| anti-rug \| degen — expands to a full ALLOW/DENY policy (the individual params above override preset values). The response echoes policyTemplate.
`minSmri`	No	Agent Financial Firewall — your policy: require SMRI >= this (0-100). Adds policy.verdict = ALLOW/DENY (fail-closed).
`amountUsd`	No	Single finite non-negative decimal USD amount, context only; does not change the score. No exponent notation or repeated values.
`minConfidence`	No	Firewall: DENY if data confidence is below this (0-1).
`denyHighRiskBand`	No	Firewall: DENY if the token-risk band is 'high'.
`denyMintAuthority`	No	Firewall: DENY if the mint authority is still set.
`denyTxMintMismatch`	No	Firewall (needs ?tx=): DENY on a CONFIRMED mismatch — the bound transaction provably does not reference the guarded mint. A tx that uses address-lookup-tables, or no tx at all, is not evaluable, so the rule passes (never a fabricated mismatch).
`denyFreezeAuthority`	No	Firewall: DENY if the freeze authority is still set.
`maxConcentrationPct`	No	Firewall: DENY if top-10 holder concentration exceeds this %.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 10, 2026

addedInput schema / properties / denyTxMintMismatch

Added value: +{
+  "description": "Firewall (needs ?tx=): DENY on a CONFIRMED mismatch — the bound transaction provably does not reference the guarded mint. A tx that uses address-lookup-tables, or no tx at all, is not evaluable, so the rule passes (never a fabricated mismatch).",
+  "type": "boolean"
+}

addedInput schema / properties / tx

Added value: +{
+  "description": "Optional base64 serialized transaction to BIND the signed authorization to: the response's authorization.subject.boundTxSha256 = sha256(tx), so your executor honors it only for that exact transaction (Proof-of-Decision per-tx). Also decoded OFFLINE to cross-check that the tx actually references the guarded mint — authorization.subject.txReferencesGuardedMint = true | false | \"unknown\".",
+  "type": "string"
+}

Changed1 schema field changedSep 9, 2026

addedInput schema / properties / policy

Added value: +{
+  "description": "Named firewall preset: conservative | bluechip | anti-rug | degen — expands to a full ALLOW/DENY policy (the individual params above override preset values). The response echoes policyTemplate.",
+  "type": "string"
+}

First observedSep 9, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden and does a strong job: it discloses that the tool returns REVIEW/unknown rather than guessing, that it is a transparent risk gate, that it does not execute actions, and that it supports per-transaction binding via tx. It adds meaningful non-obvious behavioral context beyond the schema, though it does not address externalities like rate limits or auth requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but appropriately dense; it front-loads the core purpose and output shape before adding caveats. Minor redundancy exists (e.g., restating required and optional parameters that are already in the schema), but no fluff paragraphs or tangential information are included.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 12 parameters and no output schema, the description gives a good high-level contract: output components, the fail-closed risk gate stance, and the 'not financial advice' limitation. It is complete enough for an agent to call it with the required mint and understand what the return fact family will be, though it could have added more explicit guidance on how to pick between policy presets or when to include tx=.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema description coverage is 100%, so the schema itself carries the parameter meaning. The description adds only a high-level grouping of parameters (e.g., named firewall presets, 'fail-closed' thresholds) and repeats some schema details, but it does not meaningfully deepen the understanding that the schema already provides for the 12 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific, compound function: it composes on-chain risk signals into a single EXECUTE/REVIEW/REJECT verdict plus SMRI, confidence, and evidence. It also clearly frames itself as a decision layer rather than a raw data or profit tool, though it does not explicitly contrast itself with sibling tools like solmachina_smri or solmachina_pretrade.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says it is 'the decision layer for autonomous agents' and gives prerequisites (?mint=, optional parameters), which implies the usage setting. However, it does not tell an agent when to choose this over solmachina_smri, solmachina_token_risk, or solmachina_pretrade, and gives no explicit when-not-to-use guidance, only negative disclaimers about financial advice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All solmachina-x402 tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?