pumpdata

buy_coin

Read-only

Builds a buy (or sell) of a pump.fun coin for the agent's own wallet: an unsigned Solana transaction (base64) with the pump.fun curve or PumpSwap trade and pumpdata's 0.4% fee inside it. pumpdata never holds a key: sign it with the wallet, then send it yourself or with send_tx. Expires in about a minute. For: buy this coin, ape 0.2 SOL, sell all.

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": {
      "mint": "<mint>",
      "wallet": "<wallet>"
    },
    "name": "buy_coin"
  }
}

Input Schema

Name	Required	Description
`sol`	No	SOL to spend on a buy (0.001 to 100)
`mint`	Yes	the coin's mint (base58)
`side`	No	buy (default) or sell
`tokens`	No	on a sell: raw token units, or "all"
`wallet`	Yes	the address that signs and pays
`slippage_bps`	No	default 1000 (10%)

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds behavior the annotations cannot express: a 0.4% pumpdata fee is embedded in the transaction, the trade routes through either the pump.fun curve or PumpSwap, pumpdata holds no key, and the transaction expires in about a minute. These are material operational facts (cost, custody model, time-to-live) absent from the structured hints. The unsigned-transaction framing is also consistent with readOnlyHint=true, since the tool itself performs no write.

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?

Three compact sentences, front-loaded with the verb and the artifact returned, then safety/handling, then time limit. The trailing 'For:' examples are functional usage cues rather than filler, though the parenthetical '(or sell)' in the opening slightly muddies an otherwise crisp lead.

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

Completeness5/5

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

For a six-parameter transaction-builder with no output schema, this covers what an agent needs: what is returned (base64 unsigned tx), that it expires, that it must be signed and sent, that a fee is baked in, and which sibling finishes the job. Nothing essential is missing.

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 description coverage is 100%, so every parameter is already documented, and this establishes the baseline. The description only loosely reinforces parameter meaning — 'buy this coin, ape 0.2 SOL, sell all' maps to mint/sol and the sell-all case for tokens — but adds no format, bounds, or default detail beyond what the schema already gives.

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

Purpose5/5

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

States a specific verb and resource — 'Builds a buy (or sell) of a pump.fun coin' — and immediately clarifies the output is an unsigned base64 Solana transaction rather than an executed trade. It distinguishes itself from send_tx by naming it as the downstream step, so an agent can tell the two apart without opening either schema.

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

Usage Guidelines5/5

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

Explicitly routes usage: 'sign it with the wallet, then send it yourself or with send_tx', and closes with concrete triggers ('buy this coin, ape 0.2 SOL, sell all'). Both the when-to-use and the hand-off to the sibling tool are stated rather than inferred.

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

All pumpdata 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.