agent-harnesses MCP server
Recommends, compares and searches agent harnesses from the curated best-of-Agent-Harnesses list
MCP servers that reach other models and ML platforms: generate images or audio, run embeddings, call another agent.
81 servers, page 3 of 3.
Search capabilities in this directory
Recommends, compares and searches agent harnesses from the curated best-of-Agent-Harnesses list
Typed classification, yes/no checks, scoring and ranking for coding agents via TypeSafe's Jev model
Agent evaluation and self-improvement harness exposed to MCP clients as scenarios, runs and judges
Turns PDFs, Office files and web pages into structured Docling documents, and builds or edits them
Puts budgets, verifier gates and run receipts around coding-agent jobs started from an MCP host
Start, watch and steer other AI coding CLIs running in local tmux windows from one host CLI
Local checks on LLM text for hallucination signals, prompt injection and personal data
Hosted endpoint that hands whole web tasks to Browser Use's cloud browser agent and returns the result
Hosted MCP endpoint for driving Devin: sessions, playbooks, knowledge, schedules and repo docs
LaunchDarkly's remote MCP endpoint for feature flags, AgentControl configs and observability data
One hosted OAuth endpoint for the skills, plugins, workflows and connections an OpenWork org shares
Second-opinion code and plan review from OpenAI Codex or Google Gemini inside Claude Code
Ask for human sign-off on one exact consequential agent action, then check and verify its receipt
Drives Google Flow in a local Chrome window to make videos, images, narration and captions
Typed, probability-scored judgments from TypeSafe's Jev and other System One models
Generate and edit images with Google's Gemini 2.5 Flash Image model from any MCP client
Sends questions to Perplexity's Sonar Pro, Sonar Reasoning Pro and Sonar Deep Research models
Sends prompts to the ChatGPT desktop app on a Mac and reads back its replies and conversation list
Make, edit, upscale and vectorize images, and optionally videos, on your own GPU
Chat with Meta's Muse agent through your own logged-in Chrome session
Lets an assistant transcribe local audio files to text with FunASR's SenseVoice model, entirely on-device.