autocontext
Agent evaluation and self-improvement harness exposed to MCP clients as scenarios, runs and judges
Describe the job. Find the server that can do it.
Explore real capabilities, then see what each connection can reach.
LOOKING FOR /
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
A useful server page goes beyond a name and a score. Understand the tools, choose your client, and see what the connection can access.
Explore the server field guideSubmit a public MCP server for review. Free submissions are open.