RugShield
Solana checks and free panel quote via MCP; paid parallel advisor panel via HTTP. USDC x402.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"rugshield": {
"url": "https://rugshield-x402.fly.dev/mcp/"
}
}
}Remote-Endpunkte
https://rugshield-x402.fly.dev/mcp/streamable-httphttps://getrugshield.com/mcp/streamable-httpWas es kann
Tool-Inventar
Tools (5)
🟢check_solana_transaction(transaction, signer, intent, prefer_async, idempotency_key, ...)
Use before signing an unsigned Solana transaction, not for a token mint alone. Provide a real unsigned Solana transaction serialized as base64, with optional signer and expected intent. Malformed input is rejected before payment. Simulation returns ALLOW, WARN or BLOCK with reasons and balance changes. Optional idempotency_key is random 32-byte base64url. A signed call waits up to 20 seconds for analysis and can settle without a key. If still processing, echo the unpaid job_id with the same proof and arguments when ready. get_job_result reports processing and retry_after_s for free; the result appears there only after settlement. Costs $0.01 USDC via x402.
Eingabe-Schema
{
"type": "object",
"properties": {
"transaction": {
"description": "Real unsigned Solana transaction (legacy or v0), serialized as base64; not a token mint or example placeholder.",
"title": "Transaction",
"type": "string"
},
"signer": {
"default": null,
"description": "Optional base58 Solana address that must be a required transaction signer; omit to use the fee payer.",
"title": "Signer",
"type": "string"
},
"intent": {
"additionalProperties": true,
"default": null,
"description": "Optional expected action object. Supported keys: max_sol_out (nonnegative SOL amount), expected_mints_in (array of base58 Solana token mint addresses), allowed_recipients (array of base58 Solana addresses). No other keys.",
"title": "Intent",
"type": "object"
},
"prefer_async": {
"default": false,
"description": "If work is queued or running, return a job status instead of waiting for completion. Poll get_job_result for free, then retry this tool with the same payment proof and inputs when ready; payment does not settle while processing.",
"title": "Prefer Async",
"type": "boolean"
},
"idempotency_key": {
"default": null,
"description": "Optional canonical base64url encoding of 32 random bytes. Reuse with the original payment proof and identical inputs to recover a lost reply.",
"title": "Idempotency Key",
"type": "string"
},
"job_id": {
"default": null,
"description": "Accepted job ID to echo with the original payment proof and identical inputs when recovering a call made without idempotency_key.",
"title": "Job Id",
"type": "string"
}
},
"required": [
"transaction"
],
"title": "check_solana_transactionArguments"
}🟢check_solana_token_risk(mint, prefer_async, idempotency_key, job_id)
Use before buying a pump.fun token when you have its Solana mint address. Returns advisory flags evaluated on selected historical tokens; no flags does not mean safe. Optional idempotency_key is random 32-byte base64url. A signed call waits up to 20 seconds for analysis and can settle without a key. If still processing, echo the unpaid job_id with the same proof and mint when ready. get_job_result reports processing and retry_after_s for free; the result appears there only after settlement. Costs $0.01 USDC via x402.
Eingabe-Schema
{
"type": "object",
"properties": {
"mint": {
"description": "Base58 Solana token mint address to check before buying; not a transaction or token symbol.",
"title": "Mint",
"type": "string"
},
"prefer_async": {
"default": false,
"description": "If work is queued or running, return a job status instead of waiting for completion. Poll get_job_result for free, then retry this tool with the same payment proof and inputs when ready; payment does not settle while processing.",
"title": "Prefer Async",
"type": "boolean"
},
"idempotency_key": {
"default": null,
"description": "Optional canonical base64url encoding of 32 random bytes. Reuse with the original payment proof and identical inputs to recover a lost reply.",
"title": "Idempotency Key",
"type": "string"
},
"job_id": {
"default": null,
"description": "Accepted job ID to echo with the original payment proof and identical inputs when recovering a call made without idempotency_key.",
"title": "Job Id",
"type": "string"
}
},
"required": [
"mint"
],
"title": "check_solana_token_riskArguments"
}🟢quote_solana_risk_panel(mint, advisors, chain)
Free quote for the paid HTTP panel of parallel Solana risk advisors. Pass a Solana mint and optionally comma-separated public advisor aliases from GET /v1/advisors and a CAIP-2 token chain. Returns a canonical HTTP URL and estimated total in USDC; does not call or pay advisors. The URL's HTTP 402 payment quote is authoritative. Request it without a proof, then prepay the exact original URL with a compatible x402 HTTP client. A confirmed prepayment returns 202 with job_id/status_url: poll status_url for free; no second signed request or payment is needed. Failed paid panels require support review; there is no automatic refund.
Eingabe-Schema
{
"type": "object",
"properties": {
"mint": {
"description": "Base58 Solana token mint address to analyze through the paid HTTP panel.",
"title": "Mint",
"type": "string"
},
"advisors": {
"default": null,
"description": "Optional comma-separated public advisor aliases from free GET /v1/advisors; omit to select all enabled advisors compatible with the token chain.",
"title": "Advisors",
"type": "string"
},
"chain": {
"default": null,
"description": "Optional CAIP-2 network ID of the token being analyzed, not the payment network. Defaults to Solana mainnet; other token chains are currently unsupported.",
"title": "Chain",
"type": "string"
}
},
"required": [
"mint"
],
"title": "quote_solana_risk_panelArguments"
}🟢get_job_result(job_id)
Poll an accepted job for free. A paid job reports processing, ready, or failed without revealing its result before settlement; retry_after_s gives the next polling delay, capped at two minutes. An uncertain payment reports needs_review with no automatic retry: keep the job ID and contact support without another payment. After confirmed settlement, retrieve the saved result. Read agent_guidance.payment and agent_guidance.analysis separately. Legacy charged:null means unconfirmed, not free. Historical saved replies remain unchanged; this free status tool exposes current state explanations.
Eingabe-Schema
{
"type": "object",
"properties": {
"job_id": {
"description": "Job ID returned by a paid check or accepted queued request. Poll for status without another payment; a settled result is available here.",
"title": "Job Id",
"type": "string"
}
},
"required": [
"job_id"
],
"title": "get_job_resultArguments"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Legacy opaque job identifier."
},
"job_id": {
"type": "string",
"description": "Opaque server-returned job identifier; preserve it exactly."
},
"kind": {
"type": "string",
"description": "Stored job kind when exposed; production paid checks use token_risk, tx_guard or risk_panel."
},
"status": {
"type": "string",
"enum": [
"awaiting_payment",
"queued",
"running",
"processing",
"done",
"ready",
"failed",
"payment_processing",
"needs_review"
],
"description": "Analysis and payment are separate facts. ready/done can mean work finished while its paid result is still withheld; needs_review can concern payment or analysis. Read agent_guidance.payment and analysis."
},
"status_url": {
"type": "string",
"description": "Free GET path for this existing job; no settlement or analysis restart."
},
"charged": {
"type": [
"boolean",
"null"
],
"description": "Legacy: true confirms settlement, false reports no settled charge for this attempt, null means unconfirmed. Never infer a refund or no charge from null."
},
"payment_status": {
"type": "string",
"enum": [
"reserved",
"prepared",
"claiming",
"uncertain",
"settled",
"unknown"
],
"description": "Legacy ledger or error field. Use agent_guidance.payment for the explicit charge outcome."
},
"delivery_state": {
"type": "string",
"description": "Legacy ledger state when returned by a job/retry observation."
},
"prepaid": {
"type": "boolean"
},
"created_at": {
"type": "number"
},
"eta_s": {
"type": "number",
"description": "Estimated queue delay, not a completion deadline."
},
"retry_after_s": {
"type": "integer",
"minimum": 1,
"description": "Free polling delay, not a deadline or instruction to authorize payment."
},
"next_action": {
"type": "string"
},
"error": {
"type": "string"
},
"result": {
"description": "Conditional result. Paid results are released only after confirmed settlement; token/transaction jobs expose the saved paid response envelope, while prepaid panels expose their analysis object when ready. Legacy non-purchase jobs may expose their result directly. Absence never proves no charge."
},
"agent_guidance": {
"type": "object",
"description": "Optional additive agent instructions; does not replace x402 headers or the original result.",
"properties": {
"code": {
"type": "string"
},
"next_action": {
"type": "string"
},
"payment_status": {
"type": "string",
"enum": [
"settled",
"not_charged",
"unknown"
]
},
"payment_allowed": {
"type": "boolean",
"description": "Advisory only; server preflight enforces input validity."
},
"instructions": {
"type": "array",
"items": {
"type": "string"
}
},
"examples": {
"type": "array",
"items": {
"type": "object"
}
},
"documentation": {
"type": "string"
},
"schema": {
"type": "string"
},
"request_example": {
"type": "object",
"required": [
"type",
"executable",
"explanation",
"effects",
"payment_proof_required",
"new_authorization_allowed"
],
"description": "Recommended NEXT action. A blueprint is not executable until its required original context or actual inputs are supplied. No signing or payment is performed by returning this object.",
"properties": {
"type": {
"type": "string",
"enum": [
"http",
"mcp",
"original_context",
"original_request",
"manual",
"none"
]
},
"executable": {
"type": "boolean"
},
"explanation": {
"type": "string"
},
"payment_proof_required": {
"type": "boolean"
},
"new_authorization_allowed": {
"type": "boolean"
},
"effects": {
"type": "object",
"required": [
"payment",
"analysis"
],
"properties": {
"payment": {
"type": "string",
"enum": [
"none",
"may_settle_original_authorization",
"may_settle_reviewed_authorization"
]
},
"analysis": {
"type": "string",
"enum": [
"none",
"read_operation_schema",
"read_existing_job",
"request_free_token_analysis",
"read_advisor_catalog",
"resume_or_recover_existing_job",
"start_or_complete_analysis",
"attempt_free_retry"
]
}
}
},
"method": {
"type": "string"
},
"url": {
"type": "string"
},
"url_template": {
"type": "string"
},
"requires": {
"type": "array",
"items": {
"type": "string"
}
},
"request_source": {
"type": "string"
},
"body_fields": {
"type": "object"
}
}
},
"payment": {
"type": "object",
"required": [
"status",
"charge_outcome",
"explanation",
"next_action"
],
"properties": {
"status": {
"type": "string",
"enum": [
"not_required",
"not_started",
"not_settled",
"confirmation_pending",
"settled",
"reconciliation_required",
"unconfirmed"
]
},
"charge_outcome": {
"type": "string",
"enum": [
"not_applicable",
"not_charged",
"charged",
"unconfirmed"
]
},
"explanation": {
"type": "string"
},
"next_action": {
"type": "string"
},
"new_authorization_allowed": {
"type": "boolean"
},
"background_reconciliation_available": {
"type": "boolean",
"const": false
},
"legacy_charged_note": {
"type": "string"
}
}
},
"analysis": {
"type": "object",
"required": [
"status",
"result_available",
"explanation"
],
"properties": {
"status": {
"type": "string",
"enum": [
"not_started",
"waiting_for_payment",
"queued",
"running",
"processing",
"completed",
"failed",
"review_required",
"not_reported"
]
},
"result_available": {
"type": "boolean"
},
"explanation": {
"type": "string"
}
}
}
}
},
"code": {
"type": "string",
"description": "Error code when the tool cannot fulfill this request."
},
"message": {
"type": "string"
},
"instructions": {
"type": "array",
"items": {
"type": "string"
}
},
"payment_receipt": {
"type": "object",
"description": "Decoded receipt when available after settlement; historical encoded receipts may remain only in receipt_header.",
"properties": {
"success": {
"type": "boolean"
},
"transaction": {
"type": "string"
},
"network": {
"type": "string"
}
}
},
"receipt_header": {
"type": [
"string",
"null"
],
"description": "Stored receipt when available. This is not a new payment proof to authorize or replay."
},
"status_tool": {
"type": "string",
"description": "Free tool to observe the existing retry; normally get_job_result."
}
},
"required": [
"agent_guidance"
],
"additionalProperties": true,
"description": "Free job observation or a tool error. Conditional fields preserve historical job variants. Paid panel failure can require analysis review even when payment is settled; payment and analysis are separate. Read agent_guidance.payment and analysis. A missing receipt or result does not prove no charge or refund.",
"anyOf": [
{
"required": [
"status"
]
},
{
"required": [
"code",
"message"
]
}
]
}⚪retry_failed_job(job_id)
Retry a failed paid job for free. Transaction and token checks each have one manual retry per job ID; if it still fails, keep the job ID and contact [email protected] for review. There is no automatic refund.
Eingabe-Schema
{
"type": "object",
"properties": {
"job_id": {
"description": "Job ID of a failed paid transaction or token check. Retry that job for free after get_job_result reports failure.",
"title": "Job Id",
"type": "string"
}
},
"required": [
"job_id"
],
"title": "retry_failed_jobArguments"
}Ausgabe-Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Legacy opaque job identifier."
},
"job_id": {
"type": "string",
"description": "Opaque server-returned job identifier; preserve it exactly."
},
"kind": {
"type": "string",
"description": "Stored job kind when exposed; production paid checks use token_risk, tx_guard or risk_panel."
},
"status": {
"type": "string",
"enum": [
"awaiting_payment",
"queued",
"running",
"processing",
"done",
"ready",
"failed",
"payment_processing",
"needs_review"
],
"description": "Analysis and payment are separate facts. ready/done can mean work finished while its paid result is still withheld; needs_review can concern payment or analysis. Read agent_guidance.payment and analysis."
},
"status_url": {
"type": "string",
"description": "Free GET path for this existing job; no settlement or analysis restart."
},
"charged": {
"type": [
"boolean",
"null"
],
"description": "Legacy: true confirms settlement, false reports no settled charge for this attempt, null means unconfirmed. Never infer a refund or no charge from null."
},
"payment_status": {
"type": "string",
"enum": [
"reserved",
"prepared",
"claiming",
"uncertain",
"settled",
"unknown"
],
"description": "Legacy ledger or error field. Use agent_guidance.payment for the explicit charge outcome."
},
"delivery_state": {
"type": "string",
"description": "Legacy ledger state when returned by a job/retry observation."
},
"prepaid": {
"type": "boolean"
},
"created_at": {
"type": "number"
},
"eta_s": {
"type": "number",
"description": "Estimated queue delay, not a completion deadline."
},
"retry_after_s": {
"type": "integer",
"minimum": 1,
"description": "Free polling delay, not a deadline or instruction to authorize payment."
},
"next_action": {
"type": "string"
},
"error": {
"type": "string"
},
"result": {
"description": "Conditional result. Paid results are released only after confirmed settlement; token/transaction jobs expose the saved paid response envelope, while prepaid panels expose their analysis object when ready. Legacy non-purchase jobs may expose their result directly. Absence never proves no charge."
},
"agent_guidance": {
"type": "object",
"description": "Optional additive agent instructions; does not replace x402 headers or the original result.",
"properties": {
"code": {
"type": "string"
},
"next_action": {
"type": "string"
},
"payment_status": {
"type": "string",
"enum": [
"settled",
"not_charged",
"unknown"
]
},
"payment_allowed": {
"type": "boolean",
"description": "Advisory only; server preflight enforces input validity."
},
"instructions": {
"type": "array",
"items": {
"type": "string"
}
},
"examples": {
"type": "array",
"items": {
"type": "object"
}
},
"documentation": {
"type": "string"
},
"schema": {
"type": "string"
},
"request_example": {
"type": "object",
"required": [
"type",
"executable",
"explanation",
"effects",
"payment_proof_required",
"new_authorization_allowed"
],
"description": "Recommended NEXT action. A blueprint is not executable until its required original context or actual inputs are supplied. No signing or payment is performed by returning this object.",
"properties": {
"type": {
"type": "string",
"enum": [
"http",
"mcp",
"original_context",
"original_request",
"manual",
"none"
]
},
"executable": {
"type": "boolean"
},
"explanation": {
"type": "string"
},
"payment_proof_required": {
"type": "boolean"
},
"new_authorization_allowed": {
"type": "boolean"
},
"effects": {
"type": "object",
"required": [
"payment",
"analysis"
],
"properties": {
"payment": {
"type": "string",
"enum": [
"none",
"may_settle_original_authorization",
"may_settle_reviewed_authorization"
]
},
"analysis": {
"type": "string",
"enum": [
"none",
"read_operation_schema",
"read_existing_job",
"request_free_token_analysis",
"read_advisor_catalog",
"resume_or_recover_existing_job",
"start_or_complete_analysis",
"attempt_free_retry"
]
}
}
},
"method": {
"type": "string"
},
"url": {
"type": "string"
},
"url_template": {
"type": "string"
},
"requires": {
"type": "array",
"items": {
"type": "string"
}
},
"request_source": {
"type": "string"
},
"body_fields": {
"type": "object"
}
}
},
"payment": {
"type": "object",
"required": [
"status",
"charge_outcome",
"explanation",
"next_action"
],
"properties": {
"status": {
"type": "string",
"enum": [
"not_required",
"not_started",
"not_settled",
"confirmation_pending",
"settled",
"reconciliation_required",
"unconfirmed"
]
},
"charge_outcome": {
"type": "string",
"enum": [
"not_applicable",
"not_charged",
"charged",
"unconfirmed"
]
},
"explanation": {
"type": "string"
},
"next_action": {
"type": "string"
},
"new_authorization_allowed": {
"type": "boolean"
},
"background_reconciliation_available": {
"type": "boolean",
"const": false
},
"legacy_charged_note": {
"type": "string"
}
}
},
"analysis": {
"type": "object",
"required": [
"status",
"result_available",
"explanation"
],
"properties": {
"status": {
"type": "string",
"enum": [
"not_started",
"waiting_for_payment",
"queued",
"running",
"processing",
"completed",
"failed",
"review_required",
"not_reported"
]
},
"result_available": {
"type": "boolean"
},
"explanation": {
"type": "string"
}
}
}
}
},
"code": {
"type": "string",
"description": "Error code when the tool cannot fulfill this request."
},
"message": {
"type": "string"
},
"instructions": {
"type": "array",
"items": {
"type": "string"
}
},
"payment_receipt": {
"type": "object",
"description": "Decoded receipt when available after settlement; historical encoded receipts may remain only in receipt_header.",
"properties": {
"success": {
"type": "boolean"
},
"transaction": {
"type": "string"
},
"network": {
"type": "string"
}
}
},
"receipt_header": {
"type": [
"string",
"null"
],
"description": "Stored receipt when available. This is not a new payment proof to authorize or replay."
},
"status_tool": {
"type": "string",
"description": "Free tool to observe the existing retry; normally get_job_result."
}
},
"required": [
"agent_guidance"
],
"additionalProperties": true,
"description": "Free retry admission or a tool error. Only failed token_risk and tx_guard jobs have one manual retry; risk_panel jobs are ineligible and require support review. A failed status alone does not prove retry eligibility. Read agent_guidance.payment and analysis. A missing receipt or result does not prove no charge or refund.",
"anyOf": [
{
"required": [
"status"
]
},
{
"required": [
"code",
"message"
]
}
]
}Community
Nachweis