three.ws pump.fun MCP

Swap Quote (Read-Only)

pumpfun_quote_swap

Read-only

Read-only price quote for a pump.fun AMM (PumpSwap) swap. No signing or tx sending. One of inputMint/outputMint must be wSOL (So11111111111111111111111111111111111111112). Only GRADUATED coins have an AMM pool; for a coin still on its bonding curve use get_bonding_curve instead. Pricing runs on the pool effective quote reserves (quote vault balance + pool.virtual_quote_reserves, a SIGNED i128 that is commonly negative because PumpSwap v2 trades keep waiting protocol and creator fees in the vault and subtract them there); the base side is the raw base vault balance. Returns amountOut, priceImpactBps, route, expiresAtMs, plus the reserves the quote was computed from so the number can be reproduced. Use this to size a trade on a graduated coin, or to measure its pool depth, before executing anywhere.

Input Schema

Name	Required	Description	Default
`network`	No		mainnet
`amountIn`	Yes	Input amount in raw base units (lamports for SOL).
`inputMint`	Yes	Input token mint (base58).
`outputMint`	Yes	Output token mint (base58).
`slippageBps`	No	Slippage tolerance in basis points (default 100 = 1%).

Output Schema

Name	Required	Description
`route`	Yes	AMM pool address the quote routes through (base58)
`amountOut`	Yes	Expected output amount in raw base units
`expiresAtMs`	Yes	Epoch ms after which the quote is stale
`base_reserve`	No	Raw base vault balance. Unchanged by the virtual-reserve rollout.
`quote_reserve`	No	Raw quote vault balance, before virtual reserves are added. Includes protocol and creator fees waiting for a sweep, so it overstates liquidity on its own; price on effective_quote_reserve.
`priceImpactBps`	Yes	Price impact in basis points
`virtual_quote_reserves`	No	Pool.virtual_quote_reserves, a SIGNED i128 serialized as a decimal string. Positive values add depth held outside the vault; negative values remove fees that sit in the vault waiting for a sweep (common since the PumpSwap v2 trades). Parse it as a signed integer: never unsigned, never clamped to 0, never absolute-valued.
`effective_quote_reserve`	No	quote_reserve + virtual_quote_reserves (signed addition). This is what the quote is priced against; the program guarantees it is never negative.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 9, 2026

changedOutput schema / properties / effective_quote_reserve / description

Previous value: -"quote_reserve + virtual_quote_reserves. This is what the quote is priced against."New value: +"quote_reserve + virtual_quote_reserves (signed addition). This is what the quote is priced against; the program guarantees it is never negative."

changedOutput schema / properties / quote_reserve / description

Previous value: -"Raw quote vault balance, before virtual reserves are added."New value: +"Raw quote vault balance, before virtual reserves are added. Includes protocol and creator fees waiting for a sweep, so it overstates liquidity on its own; price on effective_quote_reserve."

changedOutput schema / properties / virtual_quote_reserves / description

Previous value: -"Pool.virtual_quote_reserves. Quote-side liquidity the pool carries outside its vault. 0 on non-launchpad pools."New value: +"Pool.virtual_quote_reserves, a SIGNED i128 serialized as a decimal string. Positive values add depth held outside the vault; negative values remove fees that sit in the vault waiting for a sweep (common since the PumpSwap v2 trades). Parse it as a signed integer: never unsigned, never clamped to 0, never absolute-valued."

Changed4 schema fields changedJul 20, 2026

addedOutput schema / properties / base_reserve

Added value: +{
+  "description": "Raw base vault balance. Unchanged by the virtual-reserve rollout.",
+  "type": "string"
+}

addedOutput schema / properties / effective_quote_reserve

Added value: +{
+  "description": "quote_reserve + virtual_quote_reserves. This is what the quote is priced against.",
+  "type": "string"
+}

addedOutput schema / properties / quote_reserve

Added value: +{
+  "description": "Raw quote vault balance, before virtual reserves are added.",
+  "type": "string"
+}

addedOutput schema / properties / virtual_quote_reserves

Added value: +{
+  "description": "Pool.virtual_quote_reserves. Quote-side liquidity the pool carries outside its vault. 0 on non-launchpad pools.",
+  "type": "string"
+}

First observedJun 13, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover safety (readOnlyHint, destructiveHint=false), but the description adds real context: no signing/tx sending, the GRADUATED-only precondition, and the non-obvious pricing mechanics (effective quote reserves = vault balance + signed virtual_quote_reserves, commonly negative). That reserve methodology is exactly the kind of behavior an agent cannot infer from annotations.

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?

Front-loaded with purpose and hard constraints, and every sentence is substantive. It is on the long side and the i128 reserve aside is dense, but that detail is load-bearing for reproducing the quote rather than filler.

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 quote tool with an output schema, this covers preconditions, routing to the alternative, pricing mechanics, and a return-field summary. Nothing an agent needs to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 80% and the amountIn/network/slippage semantics are already documented. The description adds one important constraint absent from the schema: one of inputMint/outputMint must be wSOL. This materially improves correct invocation but doesn't cover every parameter detail.

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 (quote) and resource (pump.fun PumpSwap AMM swap) with the read-only scope up front. It explicitly names the sibling to use for a different case (get_bonding_curve for coins still on the bonding curve), so an agent can distinguish it without opening any 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?

Gives explicit when-to-use (size a trade on a graduated coin, measure pool depth, before executing anywhere) and when-not (bonding-curve coins -> get_bonding_curve). The alternative and the selecting condition are both named.

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

All three.ws pump.fun MCP 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.