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.
- @thinkrun/mcpprivilegedMCP serverobserved · static extractionLet your AI coding agent test its own frontend work. Connects Claude Code, Cursor, and any MCP client to your real Chrome browser — real ses
- MCP serverobserved · static extractionSideButton MCP server for AI agents — REST API, web dashboard, knowledge packs, and workflow engine
- MCP serverobserved · live tools/listHeadless browser primitives for AI agents when sites need real JS rendering.
- io.github.BitePro/chrome-debugger-mcpprivilegedMCP serverobserved · static extractionChrome breakpoint debugging MCP server for inspecting runtime values and stepping through code
- io.github.collapseindex/ci1t-mcpprivilegedMCP serverobserved · static extractionCI-1T prediction stability engine. Detect ghosts, evaluate drift, monitor fleets. 20 tools.
- io.github.noncelogic/mcpprivilegedMCP serverobserved · static extractionHosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
- io.github.pipeworx-io/mathjsprivilegedMCP serverobserved · static extractionMath.js MCP — wraps the mathjs.org API (free, no auth)
- io.github.sidebutton/sidebuttonprivilegedMCP serverobserved · static extractionOpen-source MCP server with browser automation and knowledge packs for AI agents
- io.github.superlowburn/agentrankprivilegedMCP serverobserved · static extractionGoogle for AI agents. Gives your AI live search across 25,000+ scored MCP servers and tools.