Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/serbyte-development/image-search-mcp/install-mcpnpx skills add serbyte-development/image-search-mcp --skill install-mcpgit clone --depth 1 https://github.com/serbyte-development/image-search-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/serbyte-development/image-search-mcp/install-mcp)<a href="https://agentmods.dev/skills/serbyte-development/image-search-mcp/install-mcp"><img src="https://agentmods.dev/badge/skills/serbyte-development/image-search-mcp/install-mcp.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.00666 |
| Opus 5 | $0.00029 | $0.00333 |
| Sonnet 5 | $0.00012 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
install-image-search-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Image Search MCP
Repository: https://github.com/Serbyte-Development/image-search-mcp
Goal
Install the MCP server locally, configure provider API keys, add it to the user's MCP client, and verify that the tools are available.
Instructions
-
Determine the user's operating system and MCP client from context or local inspection when possible. Ask only if it cannot be determined.
-
Prefer a packaged install instead of cloning the repository:
brew install Serbyte-Development/tap/image-search-mcpIf Homebrew is unavailable or the formula has not been published yet, use:
pipx install --backend pip git+https://github.com/Serbyte-Development/image-search-mcp.gitFall back to cloning + a virtual environment only if neither packaged path is available.
-
Ask the user for whichever provider API keys they want to use. At least one provider must be configured:
PEXELS_API_KEYUNSPLASH_ACCESS_KEYPIXABAY_API_KEY
Never print, commit, or expose secret values.
-
Configure the user's MCP client to launch the installed
image-search-mcpcommand and pass the provider keys as environment variables.Example configuration shape:
{ "mcpServers": { "image-search": { "command": "image-search-mcp", "env": { "PEXELS_API_KEY": "...", "UNSPLASH_ACCESS_KEY": "...", "PIXABAY_API_KEY": "..." } } } }Only include keys the user actually configured. If the client requires a remote MCP endpoint instead of stdio, help the user deploy their own copy to Vercel, configure the provider keys as Vercel environment variables, and connect to
https://<project>.vercel.app/mcp. Do not use the maintainer's deployment. Verify the endpoint after deployment; if host validation returns HTTP 421, expose Vercel system environment variables or setIMAGE_SEARCH_MCP_ALLOWED_HOSTSto the deployment host.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 76 lines · 58 tokens per session scan A f621279503c7
install-image-search-mcp is a skill published in the GitHub repository serbyte-development/image-search-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 58 tokens to every session and 666 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
user-usecases
Database of real user use cases for APIbase platform. Contains detailed examples of how specific APIs are onboarded, wrapped, and served to AI agents. Use this skill when you need to reference real integration examples, explain the APIbase onboarding process, or design new API wrappers based on proven patterns.
@elad12390/web-research-assistant
Comprehensive MCP server for web research with 14 tools: SearXNG + Exa AI search, URL crawling, stealth scraping (Cloudflare bypass), package registry lookup (npm/PyPI/crates), GitHub stats, changelog fetching, tech comparison, error translation, API docs discovery, stock image search, and service health. Trigger…
business-model-validator
Use when a prospect, new customer, or existing operator wants to know whether Zooza fits their business, or which Zooza features map to how they operate. No Zooza account required — works as a pure knowledge interview.
pr
Use for any GitHub Pull Request work. Auto-detects lifecycle phase (create / update / report) from current state — only requires explicit command for status, comments, or merge. Triggered by /pr, 'PR', 'create PR', 'open PR', 'update PR', 'PR status', 'merge PR'. Suggests, never auto-creates without user invocation.
ci
Use when the user wants CI status, failed-job logs, or help fixing a red build. Triggered by /ci, 'CI status', 'check the build', 'fix CI', 'why is CI failing', 'look at the build'. Auto-routes by state: status / logs / fix-proposal. Reads logs locally — never re-triggers builds without explicit user command.
orca
Orchestrator mode — the default working mode of this project, not a toggle to find. The main agent does no task work itself: every unit goes to a role-framed subagent that inherits its model and effort, at most 5 in parallel unless overridden. Load it for the contract (roles, width, write scopes, verification), when…