Skip to main content
Glama

SolGuard Solana Token-2022 Scanner & Safe-Swap Router

Build Unsigned Jito Safe-Swap (v0 Transaction)

build_jito_safe_swap
Read-only

Builds an unsigned Solana v0 VersionedTransaction via Jupiter v1 + atomic 65 bps SolGuard fee transfer + Jito bundleOnly=true MEV protection (supports side='buy' SOL->Token after anti-rug verification, or side='sell' Token->SOL post-unwrap Safe-Exit).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "userPublicKey": "<userPublicKey>",
      "outputMint": "<outputMint>"
    },
    "name": "build_jito_safe_swap"
  }
}

Input Schema

NameRequiredDescriptionDefault
sideNoTrade direction: 'buy' (SOL->Token) or 'sell' (Token->SOL)buy
sellPctNoOptional wallet ATA percentage (1-100) when side='sell'
amountRawNoOptional integer base units when side='sell'
amountSolNoSwap input amount in SOL (0.0001 to 10000)
inputMintNoInput mint Base58 (defaults to native WSOL on buy)So11111111111111111111111111111111111111112
outputMintYesTarget Solana token mint Base58 address
slippageBpsNoMax slippage in basis points (10 to 3000, default 100)
amountTokensNoOptional UI token quantity when side='sell'
userPublicKeyYesUser Solana wallet Base58 public key (fee payer & signer)
referrerPubkeyNoOptional partner Solana wallet Base58 pubkey for atomic 45/20 bps revenue split (earns 20 bps)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=false, and openWorldHint=true, but the description adds real context: the output is unsigned (nothing is signed or broadcast), a 65 bps fee transfer is embedded atomically, Jito bundleOnly=true is enforced, and a gate condition on side='buy'. Notably it does not clarify that readOnlyHint refers only to construction, not to the funds-moving nature of the resulting transaction.

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?

A single dense sentence that leads with the verb and artifact, with no filler. It is jargon-heavy but every clause carries information, so it earns its length.

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

Completeness3/5

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

For a 10-parameter transaction-construction tool with no output schema, the description should say what comes back (serialized transaction, recent blockhash, required signers, bundle tips). It is silent on the return shape and on whether the returned transaction must be signed or submitted to a Jito block engine separately.

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?

Schema coverage is 100%, so per-parameter meaning is already fully documented in the schema. The description adds only light framing: the buy/sell direction meanings and the fact that the referrer participates in a 45/20 bps split of the 65 bps fee, without explaining the interplay between amountRaw, amountTokens, and sellPct for sell-side sizing.

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 names a specific verb and artifact: building an unsigned Solana v0 VersionedTransaction, with the exact routing stack (Jupiter v1), fee (65 bps SolGuard), and MEV posture (Jito bundleOnly=true) spelled out. It distinguishes buy vs sell semantics, which differentiates it in substance from build_jito_safe_exit, but it never names that sibling as an alternative.

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?

Sequencing is implied rather than stated: 'after anti-rug verification' points at solana_token_forensic_audit and 'post-unwrap Safe-Exit' points at build_jito_safe_exit, but neither is named nor is any explicit 'call X first' or 'do not use this when...' guidance given. An agent can infer the workflow only by reading carefully.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources