Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
Read-only MCP (Model Context Protocol) server that connects coding agents to the AgentGuard Read API. Use it after the local SDK is already in place and you want Codex, Claude Code, Cursor, or another MCP client to inspect traces, decision events, alerts, usage, costs, and budget health. The boundary is deliberate: The SDK proves runtime enforcement locally The MCP server gives coding agents a…
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
query_tracesNo description publishedThis tool published no description. Forge does not invent one.
get_traceNo description publishedThis tool published no description. Forge does not invent one.
get_trace_decisionsNo description publishedThis tool published no description. Forge does not invent one.
get_alertsNo description publishedThis tool published no description. Forge does not invent one.
get_usageNo description publishedThis tool published no description. Forge does not invent one.
get_costsNo description publishedThis tool published no description. Forge does not invent one.
check_budgetNo description publishedThis tool published no description. Forge does not invent one.
0 of 7 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Read-only MCP (Model Context Protocol) server that connects coding agents to the AgentGuard Read API. Use it after the local SDK is already in place and you want Codex, Claude Code, Cursor, or another MCP client to inspect traces, decision events, alerts, usage, costs, and budget health. The boundary is deliberate: The SDK proves runtime enforcement locally The MCP server gives coding agents a narrow read surface over retained data The hosted dashboard stays the operational control plane Tool |…
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This package was last scanned before Forge began storing the resolved tree. The next scan will record it.