Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
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.
AGENTGUARD_LICENSE_KEYAPI keyoptionalOptional AgentGuard license key for license validation and seat registration. Otherwise read from local configuration.
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
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.
spend_decideGate a model call BEFORE it runs. Pass metadata only (model, token counts, endpoint URL), never prompt content. Returns allow/block plus an Ed25519-signed, content-free receipt with model and hosting provenance (weights origin, jurisdiction, retention). Unknown self-hosted models need set_model_cos…Gate a model call BEFORE it runs. Pass metadata only (model, token counts, endpoint URL), never prompt content. Returns allow/block plus an Ed25519-signed, content-free receipt with model and hosting provenance (weights origin, jurisdiction, retention). Unknown self-hosted models need set_model_cos…
it runs. Pass metadata only (model, token counts, endpoint URL), never prompt content. Returns allow…No input schema was published for this tool.
verify_receiptIndependently verify an AgentGuard signed receipt. Returns valid true/false. Tampering with any signed field makes verification fail.Independently verify an AgentGuard signed receipt. Returns valid true/false. Tampering with any signed field makes verification fail.
No input schema was published for this tool.
export_receiptsExport the tenant decision ledger, including earlier process runs, as a hash-chained array of signed receipts with a chain verification result. Memory mode exports this process only.Export the tenant decision ledger, including earlier process runs, as a hash-chained array of signed receipts with a chain verification result. Memory mode exports this process only.
No input schema was published for this tool.
set_model_costRegister a cost for a model with no built-in pricing (required for self-hosted models: AgentGuard fails closed on unknown costs). Cents per 1,000 tokens.Register a cost for a model with no built-in pricing (required for self-hosted models: AgentGuard fails closed on unknown costs). Cents per 1,000 tokens.
No input schema was published for this tool.
provenance_previewPreview the provenance AgentGuard would attest for a model and endpoint WITHOUT spending: model identity, weights origin country (China-origin families flagged), hosting jurisdiction, retention posture.Preview the provenance AgentGuard would attest for a model and endpoint WITHOUT spending: model identity, weights origin country (China-origin families flagged), hosting jurisdiction, retention posture.
No input schema was published for this tool.
spend_statusShow the active policy: caps, tenant, enforcement mode, decisions so far this session, and the signer identity.Show the active policy: caps, tenant, enforcement mode, decisions so far this session, and the signer identity.
No input schema was published for this tool.
6 of 6 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.
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
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)
57 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+45 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.