GiphySAFE
An implementation of Giphy integration with Model Context Protocol
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/magarcia/mcp-server-giphy/actions/workflows/ci.yml) [](https://www.npmjs.com/package/mcp-server-giphy) [](https://www.npmjs.com/package/mcp-server-giphy) [](https://opensource.org/licenses/MIT)
MCP Server for the Giphy API, enabling AI models to search, retrieve, and utilize GIFs from Giphy.
Features
- Content Filtering: Filter results by rating (G, PG, PG-13, R) to ensure appropriate content
- Optimized Response Format: Response data optimized for AI model consumption
- Multiple Search Methods: Support for query-based, random, and trending GIF retrieval
- Comprehensive Metadata: Each GIF comes with full metadata including dimensions, formats, and attribution
- Pagination Support: Control result size and pagination for efficient API use
Tools
search_gifs
- Search for GIFs on Giphy with a query string
- Inputs:
query(string): Search query term or phraselimit(optional number): Maximum number of objects to return (default: 10, max: 50)offset(optional number): Results offset (default: 0)rating(optional string): Content rating (g, pg, pg-13, r)lang(optional string): Language code (default: en)- Returns: Array of GIF objects with metadata
get_random_gif
- Get a random GIF from Giphy, optionally filtered by tag
- Inputs:
tag(optional string): Tag to limit random resultsrating(optional string): Content rating (g, pg, pg-13, r)- Returns: Random GIF object with metadata
get_trending_gifs- Get currently trending GIFs on Giphy
- Inputs:
limit(optional number): Maximum number of objects to return
ce33e0e13e0cOBSERVED · 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 mcp-server-giphy --env GIPHY_API_KEY=${GIPHY_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"mcp-server-giphy": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GIPHY_API_KEY": "${GIPHY_API_KEY}"
}
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_random_gif | read | Get a random GIF from Giphy, optionally filtered by tag |
get_trending_gifs | read | Get currently trending GIFs on Giphy |
search_gifs | read | Search for GIFs on Giphy with a query string |
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 (3)
@modelcontextprotocol/sdk, axios, dotenv, @eslint/js, @types/jest, @types/node, @typescript-eslint/eslint-plugin, @typescript-eslint/parser
load_dotenv() # load environment variables from .env
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass.
ce33e0e13e0cfull audit observations/trust-audit/mcp-server/magarcia__giphy.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 | ce33e0e13e0c | SAFE | B | 89 | first audit |
Questions
What is the Giphy MCP server?
An implementation of Giphy integration with Model Context Protocol
What tools does Giphy expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Giphy 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 Giphy need?
It reads GIPHY_API_KEY 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 Giphy run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-server-giphy at 1.0.3.
How current is this page?
The grade is for one exact copy of the source (ce33e0e13e0c), read on 2026-10-08. The repository is watched and re-audited when it changes.