MCP package manager with trust scoring. Search, install, and audit MCP servers.
The MCP package manager that guards your AI's tools at runtime -- search, install, audit, and inspect every MCP server from your terminal. The risky part of an MCP server doesn't show up at install -- it shows up while your agent is running: prompt injection hidden in a tool's output, a server that quietly rewrites its tools after you approved them, a sampling request that smuggles instructions…
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.
read_threadNo description publishedThis tool published no description. Forge does not invent one.
mcpm_searchNo description publishedThis tool published no description. Forge does not invent one.
mcpm_installNo description publishedThis tool published no description. Forge does not invent one.
mcpm_infoNo description publishedThis tool published no description. Forge does not invent one.
mcpm_listNo description publishedThis tool published no description. Forge does not invent one.
mcpm_removeprivilegedNo description publishedThis tool published no description. Forge does not invent one.
mcpm_auditNo description publishedThis tool published no description. Forge does not invent one.
mcpm_doctorNo description publishedThis tool published no description. Forge does not invent one.
mcpm_setupNo description publishedThis tool published no description. Forge does not invent one.
mcpm_upNo description publishedThis tool published no description. Forge does not invent one.
0 of 10 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.
The MCP package manager that guards your AI's tools at runtime -- search, install, audit, and inspect every MCP server from your terminal. The risky part of an MCP server doesn't show up at install -- it shows up while your agent is running: prompt injection hidden in a tool's output, a server that quietly rewrites its tools after you approved them, a sampling request that smuggles instructions into your model. mcpm scores every install for hardcoded secrets, prompt injection, and typosquatting…
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.