MCP security guard and package manager: block prompt injection, tool poisoning and rug-pulls in Model Context Protocol servers at runtime; trust-scored installs for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI.
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_threadRead the contents of a chat thread.Read the contents of a chat thread.
No input schema was published for this tool.
mcpm_searchSearch the MCP registry for servers with trust scoresSearch the MCP registry for servers with trust scores
No input schema was published for this tool.
mcpm_installprivilegedInstall an MCP server with trust assessmentInstall an MCP server with trust assessment
No input schema was published for this tool.
mcpm_infoShow full details and trust score for an MCP serverShow full details and trust score for an MCP server
No input schema was published for this tool.
mcpm_listList installed MCP servers across AI clientsList installed MCP servers across AI clients
No input schema was published for this tool.
mcpm_removeprivilegedRemove an MCP server from client configsRemove an MCP server from client configs
No input schema was published for this tool.
mcpm_auditScan all installed servers and produce trust reportScan all installed servers and produce trust report
No input schema was published for this tool.
mcpm_doctorCheck MCP setup healthCheck MCP setup health
No input schema was published for this tool.
mcpm_setupInstall MCP servers from a natural language descriptionInstall MCP servers from a natural language description
No input schema was published for this tool.
mcpm_upInstall all servers from an mcpm.yaml stack file with trust verification. Equivalent to docker-compose up for MCP servers. Runs trust re-assessment and blocks servers that violate the trust policy. Pass profile to install only servers matching that profile, or dryRun to preview what would be instal…Install all servers from an mcpm.yaml stack file with trust verification. Equivalent to docker-compose up for MCP servers. Runs trust re-assessment and blocks servers that violate the trust policy. Pass profile to install only servers matching that profile, or dryRun to preview what would be instal…
No input schema was published for this tool.
10 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.
MCP security guard and package manager: block prompt injection, tool poisoning and rug-pulls in Model Context Protocol servers at runtime; trust-scored installs for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
77 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+65 more not listed. The counts by reason above cover all of them.
Not followed: optionalDependencies, peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.