dexe-mcp

Upload a DAO avatar (one-shot: pins + returns avatarCID/avatarFileName/avatarUrl)

dexe_ipfs_upload_avatar

Upload and pin a validated JPEG, PNG, WebP, or GIF avatar to IPFS, returning its CID, filename, and URL for use in DeXe DAO profiles.

Instructions

Writes to a remote service. Pins an image, returning {avatarCID, avatarFileName, avatarUrl}. PREFER filePath; never pass base64 through the conversation. Magic-byte validated (JPEG/PNG/WebP/GIF only — SVG/HTML render broken on app.dexe.io); renamed .jpeg; CID v1 base32.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "dexe_ipfs_upload_avatar"
  }
}

Input Schema

Name	Required	Description	Default
`base64`	No	Base64 image bytes — only when the image isn't a local file.
`fileName`	No	Base filename; extension will be normalized to .jpeg	avatar
`filePath`	No	Absolute path to a local image (JPEG/PNG/WebP/GIF, max 10 MB). Preferred over base64.
`contentType`	No	Caller-claimed MIME type. Informational only — the pinned MIME comes from byte sniffing.	image/jpeg

Output Schema

Name	Required	Description
`size`	Yes
`pinnedAt`	Yes
`avatarCID`	Yes	CID v1 base32 — pass to upload_dao_metadata as avatarCID.
`avatarUrl`	Yes	Full subdomain-gateway URL — what the frontend stores verbatim.
`avatarFileName`	Yes	Filename (always ends with .jpeg).
`detectedFormat`	Yes	Raster format detected from magic bytes (jpeg\|png\|webp\|gif).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.37.1Nov 11, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes well beyond that by disclosing that this writes to a remote service, that the asset is pinned (persisted), that MIME is determined by magic-byte sniffing rather than the caller's claim, that SVG/HTML render broken on app.dexe.io, and that the filename is renamed to .jpeg. It stops short of stating whether pins are public/irreversible or what auth/permissions or rate limits apply, which is the remaining gap for a write operation.

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?

Six short clauses, front-loaded with the fact that this is a remote write, followed by the return shape and then the practical constraints. There is no filler; every clause carries a distinct operational fact.

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?

With an output schema present, the description does not need to explain return values, and annotations cover the safety profile, so the remaining burden is behavioral. It covers validation, naming, and format limits but omits permissions/auth and the permanence or visibility of the resulting pin, which matter for a one-shot write.

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 100%, so the baseline is 3; the description still adds real meaning by flagging that base64 should not be routed through the conversation and by explaining the extension-normalization and validation behavior that governs fileName/contentType. The 'prefer filePath' advice partially duplicates the schema text, which keeps it from a 5.

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 action and payload: it pins an image and returns a concrete object with avatarCID/avatarFileName/avatarUrl, so an agent knows exactly what comes back. It does not, however, distinguish itself from the sibling dexe_ipfs_upload_file or dexe_dao_generate_avatar, so the avatar-specific role is only carried by the tool name/title, not the description body.

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?

Guidance is limited to a parameter preference ('PREFER filePath; never pass base64 through the conversation') and a format constraint (JPEG/PNG/WebP/GIF only). There is no statement about when to choose this tool over dexe_ipfs_upload_file or dexe_dao_generate_avatar, or what preconditions exist, so the agent must infer the selection rule from the name.

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

Deploy Server