~/agentstafferAgentStaffer
Find, trial, compare, and govern AI agents before hiring
Roles / Technical Category
Review matching candidates
Next best action: Open a profile, compare evidence, then run a sandbox trial
MCP & Tool Integration
MCP servers, tool-use layers, SDK adapters, and integrations that connect agents to external tools.
4993total
4993filtered
5page
417pages
Category fit
Which technical function should the agent perform?
Filter candidates by capability, protocol, trust, install readiness, and trial status.
- Connect agents to tools, MCP servers, SDKs, or external APIs.
- Review install manifests and permissions.
- Confirm client compatibility before local setup.
Recommended trials and bundles
mcpservers / skill
pyrefly-type-coverage
Migrate a file to use stricter Pyrefly type checking with annotations required for all functions, classes, and attributes.
MCPHTTPCLI
- Fit
- 77 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
playbooks / skill
triaging-issues skill by pytorch/pytorch
This skill triages GitHub issues by routing to oncall teams, applying labels, and posting first-line responses to streamline resolution.
MCPCLIHTTP
- Fit
- 77 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
playbooks / skill
metal-kernel skill by pytorch/pytorch
This skill helps you implement native Metal kernels for PyTorch operators on Apple Silicon, boosting performance and MPS support.
MCPCLIHTTP
- Fit
- 77 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
mcpservers / skill
open-source
Reference docs for writing Python code against the browser-use library. Read the relevant file based on what the user needs.
MCPHTTPCLI
- Fit
- 77 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
github / workflow
browser-use/browser-use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
HTTPMCPCLI
- Fit
- 77 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
mcpservers / skill
remote-browser
Cloud browser automation for sandboxed agents without local GUI access. Supports navigation, page inspection, interactions, JavaScript execution, and cookie management via 30+ CLI commands Includes cloud session management for running autonomous browser agents in parallel, with task monitoring and structured output options Provides local dev server tunnelin...
MCPHTTPCLI
- Fit
- 77 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
playbooks / skill
playwright-dev skill by microsoft/playwright
This skill explains how to develop Playwright by adding APIs, MCP tools, CLI commands, and vendor dependencies for maintainable core.
MCPHTTPCLI
- Fit
- 77 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
github / skill
IvanMurzak/Unity-MCP
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
MCPCLIHTTPSDK
- Fit
- 77 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
mcpservers / tool
Cloudflare MCP Server
Deploy, configure & interrogate your resources on the Cloudflare developer platform (e.g. Workers/KV/R2/D1) Browse Cloudflare MCP Server for Claude,...
MCPHTTPCLISDK
- Fit
- 77 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
mcpservers / skill
workflow
Vercel Workflow DevKit (WDK) expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries,…
MCPHTTPCLISDK
- Fit
- 77 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
mcpservers / tool
Browserbase MCP Server
Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more) Browse Browserbase MCP Server for Claude,...
MCPHTTPCLISDK
- Fit
- 77 / 100
- Trust
- Needs review
- Install
- MCP ready
Review links
playbooks / skill
typescript skill by lobehub/lobehub
This skill helps you write cleaner, safer TypeScript by applying code style, type-safety, and performance guidelines across projects.
MCPHTTPCLI
- Fit
- 76 / 100
- Trust
- High traction
- Install
- MCP ready
Review links
Review support
Open Category guide
Review links
Technical category pages stay focused on job browsing; complete review records and finalist profile resources stay linked here.
Supporting review linksLinks, review order, and page-specific notes remain available here.
Category guideTechnical role guideAgent inventoryResource mapReview guideAPI referenceSite contextSitemapProfile resources
4993 matching candidates for MCP & Tool Integration. Open candidate profiles for fit, setup guidance, trust evidence, and sandbox trial planning.
- 01Site contextShared review rules
- 02Role categoryOpen the focused review record
- 03Agent inventoryBrowse the matching inventory
- 04Profile resourcesEvidence, setup, trust, trial, and history files
Use the links and review path below for role-category candidates, related playbooks, and finalist profile resources before action.
Review route: OpenAI review tools can start with openai.json; otherwise use site context and agent inventory before opening the finalist's complete review materials before install, hire, or promotion.