PollinationsSAFE
An MCP server that enables AI assistants to generate images, text, and audio through the Pollinations APIs. Please see the newer MCP server, Nectar-MCP. Link below
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
This server is archived as it no longer works with Pollinations newer API. Please see [Nectar-MCP](https://github.com/pinkpixel-dev/nectar-mcp) for my new Pollinations MCP server, specifically for image generation, image editing, and video generation.
A Model Context Protocol (MCP) server that enables AI assistants to generate images, text, and audio through the Pollinations APIs
[](https://smithery.ai/server/@pinkpixel-dev/mcpollinations) [](https://mseep.ai/app/8448e4ec-c863-476a-8adb-aed3cf16ea2b)
Features
- Generate image URLs from text prompts
- Generate images and return them as base64-encoded data AND save as png, jpeg, jpg, or webp (default: png)
- Generate text responses from text prompts
- Generate audio responses from text prompts
- List available image and text generation models
- No authentication required
- Simple and lightweight
- Compatible with the Model Context Protocol (MCP)
System Requirements
- Node.js: Version 14.0.0 or higher
- For best performance, we recommend Node.js 16.0.0 or higher
- Node.js versions below 16 use an AbortController polyfill
Quick Start
Installing via Smithery
To install mcpollinations for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @pinkpixel-dev/mcpollinations --client claude
The easiest way to use the MCP server:
# Run directly with npx (no installation required) npx @pinkpixel/mcpollinations
If you prefer to install it globally:
# Install globally npm install -g @pinkpixel/mcpollinations # Run the server mcpollinations # or npx @pinkpixel/mcpollinations
Or clone the repository:
# Clone the git repository git clone https://github.com/pinkpixel-dev/mcpollinations.git # Run the server mcpolli
74633c9d0821OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcpollinations --env POLLINATIONS_TOKEN=${POLLINATIONS_TOKEN} --env TOKEN=${TOKEN} -- npx -y @pinkpixel/[email protected]{
"mcpServers": {
"mcpollinations": {
"command": "npx",
"args": [
"-y",
"@pinkpixel/[email protected]"
],
"env": {
"POLLINATIONS_TOKEN": "${POLLINATIONS_TOKEN}",
"TOKEN": "${TOKEN}"
}
}
}
}Exposed tools (9)
7 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
editImage | write | Edit or modify an existing image based on a text prompt. User-configured settings in MCP config will be used as defaults unless specifically overridden. |
generateImage | write | Generate an image, return the base64-encoded data, and save to a file by default. User-configured settings in MCP config will be used as defaults unless specifically overridden. |
generateImageFromReference | read | Generate a new image using an existing image as reference. User-configured settings in MCP config will be used as defaults unless specifically overridden. |
generateImageUrl | read | Generate an image URL from a text prompt. User-configured settings in MCP config will be used as defaults unless specifically overridden. |
listAudioVoices | read | List all available audio voices for text-to-speech generation |
listImageModels | read | List available image models |
listTextModels | read | List available text models |
respondAudio | read | Generate an audio response to a text prompt and play it through the system |
respondText | read | Respond with text to a prompt using the Pollinations Text API. User-configured settings in MCP config will be used as defaults unless specifically overridden. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, @pinkpixel/mcpollinations, node-abort-controller, node-fetch, play-sound
Gates applied: no_behavioural_pass.
74633c9d0821full audit observations/trust-audit/mcp-server/pinkpixel-dev__pollinations-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 74633c9d0821 | SAFE | B | 89 | first audit |
Questions
What is the Pollinations MCP server?
An MCP server that enables AI assistants to generate images, text, and audio through the Pollinations APIs. Please see the newer MCP server, Nectar-MCP. Link below
What tools does Pollinations expose?
9 in total: 7 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Pollinations safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Pollinations need?
It reads POLLINATIONS_TOKEN and TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Pollinations run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @pinkpixel/mcpollinations at 1.3.1.
How current is this page?
The grade is for one exact copy of the source (74633c9d0821), read on 2026-10-08. The repository is watched and re-audited when it changes.