get_trace

6 registry entries were observed exposing a tool named get_trace — none of them flagged as a privileged capability.

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,491 of 26,663 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. @spanlens/mcp-serververified
   trust 85/100 · AMCP serverobserved 2026-06-14 · static extraction
   Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.
2. @intencion/mcp
   trust 60/100 · BMCP serverobserved 2026-08-09 · static extraction
   MCP server for debugging AI-agent runs from your editor with Intencion. Lets Claude Code and Cursor explain why an agent run failed, with ev
3. io.github.bmdhodl/agentguard47
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
4. io.github.LumabyteCo/clarifyprompt
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   AI prompt optimization for 58+ platforms across 7 categories with custom platforms
5. io.github.mdfifty50-boop/trace-forge
   trust 60/100 · BMCP serverobserved 2026-06-13 · static extraction
   Structured execution trace and span logging for AI agents
6. slang-workflows
   trust 60/100 · BMCP serverobserved 2026-08-13 · static extraction
   Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

All indexed toolsSearch the registry for get_trace