evaluate

9 registry entries were observed exposing a tool named evaluate — 7 of them as a privileged capability (a name matching exec / write / delete keywords).

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,470 of 26,658 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.

  1. @thinkrun/mcpprivileged
    trust 60/100 · BMCP serverobserved · static extraction
    Let your AI coding agent test its own frontend work. Connects Claude Code, Cursor, and any MCP client to your real Chrome browser — real ses
  2. trust 60/100 · BMCP serverobserved · static extraction
    SideButton MCP server for AI agents — REST API, web dashboard, knowledge packs, and workflow engine
  3. trust 60/100 · BMCP serverobserved · live tools/list
    Headless browser primitives for AI agents when sites need real JS rendering.
  4. trust 60/100 · BMCP serverobserved · static extraction
    Chrome breakpoint debugging MCP server for inspecting runtime values and stepping through code
  5. trust 60/100 · BMCP serverobserved · static extraction
    CI-1T prediction stability engine. Detect ghosts, evaluate drift, monitor fleets. 20 tools.
  6. trust 60/100 · BMCP serverobserved · static extraction
    Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
  7. trust 60/100 · BMCP serverobserved · static extraction
    Math.js MCP — wraps the mathjs.org API (free, no auth)
  8. trust 60/100 · BMCP serverobserved · static extraction
    Open-source MCP server with browser automation and knowledge packs for AI agents
  9. trust 60/100 · BMCP serverobserved · static extraction
    Google for AI agents. Gives your AI live search across 25,000+ scored MCP servers and tools.

All indexed toolsSearch the registry for evaluate