Skip to main content
Glama

three.ws pump.fun MCP

by io.github.nirholas

Upload Coin Metadata

pumpfun_upload_metadata
Idempotent

Upload coin metadata (name, symbol, description, image) to IPFS and get back a pump.fun-ready metadata URI. Call this before launching a coin — pass the returned uri to the launch-agent endpoint or the studio launch flow. Requires a valid bearer token (API key). Image may be a public HTTPS URL or a base64 data URI (max 10 MB). The returned uri is a permanent ipfs:// link; the call is idempotent for the same content.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesCoin name (1–32 chars).
symbolYesTicker symbol (1–10 chars, no $).
twitterNoTwitter/X handle or URL (optional).
websiteNoWebsite URL (optional).
telegramNoTelegram URL (optional).
image_urlYesImage for the coin icon. Public HTTPS URL or base64 data URI (data:image/png;base64,…). Square image, at least 400×400 px, under 5 MB.
descriptionYesCoin description (max 500 chars).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
cidYesIPFS CID of the metadata JSON.
uriYesipfs:// URI ready for the pump.fun launch-agent `uri` field.
providerNoIPFS provider used.
image_cidNoIPFS CID of the uploaded image.

TDQS

A4.2/5.0
Behavior4/5

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

The description discloses idempotency (matching idempotentHint=true), the need for an API key, image constraints (max 10 MB, format), and that the returned URI is permanent. This adds value beyond annotations.

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

Conciseness5/5

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

The description is concise at 5 sentences, each serving a purpose: main action, usage flow, auth, image format/size, and idempotency/permanence. It is front-loaded with the core function and contains no fluff.

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?

The description adequately covers the tool's purpose, inputs, output, and prerequisites. With an output schema present, the description doesn't need to detail return values. It provides sufficient context for an agent to use the tool correctly.

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?

All 7 parameters are documented in the schema with constraints (e.g., name 1-32 chars). The description doesn't add extra detail per parameter, but schema coverage is 100%, so the baseline is 3. The main contribution is explaining the overall flow, not parameter specifics.

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?

The description clearly states the tool uploads coin metadata to IPFS and returns a metadata URI, specifying the verb (upload) and resource (coin metadata). It distinguishes from siblings like get_coin_intel and pumpfun_quote_swap, which handle different operations.

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

Usage Guidelines4/5

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

The description explicitly says to call this tool before launching a coin and to pass the returned URI to the launch-agent or studio launch flow. It also notes the requirement for a bearer token. While it doesn't list alternatives, the context from sibling tools makes the usage clear.

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0
Disambiguation4/5

Most tools have distinct purposes, but get_coin_intel and get_oracle_conviction overlap in providing intelligence signals; descriptions help differentiate but still may cause confusion.

Naming Consistency3/5

Naming patterns are mixed: some use snake_case (get_bonding_curve), others use camelCase (sns_reverseLookup), and kol_leaderboard lacks a prefix that others like pumpfun_ have.

Tool Count4/5

19 tools cover a broad range of pump.fun functionality, from token details to claims and social analysis; the count feels appropriate for the scope.

Completeness5/5

The tool set covers virtually all core aspects of pump.fun ecosystem: token info, intelligence, trading, claims, AMM quotes, metadata upload, SNS, and social sentiment, with no obvious gaps.

Resources