Thrd MCP: agent email tools for events/threads, safe send/reply, usage, trust and security.
Expose Thrd (Agent Email) as an MCP server so AI clients can: Poll inbound email events Read threads and messages Reply and send outbound (policy-gated) Check usage, trust score, and security analysis This lives in the monorepo under . : your Thrd agent API key : for stateless mode (no session ids). Default is stateful. : if set, requires on every request Instant onboarding tool gate: If…
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.
thrd.healthNo description publishedThis tool published no description. Forge does not invent one.
thrd.poll_eventsNo description publishedThis tool published no description. Forge does not invent one.
thrd.ack_eventsNo description publishedThis tool published no description. Forge does not invent one.
thrd.list_threadsNo description publishedThis tool published no description. Forge does not invent one.
thrd.get_thread_messagesNo description publishedThis tool published no description. Forge does not invent one.
thrd.replyNo description publishedThis tool published no description. Forge does not invent one.
thrd.sendNo description publishedThis tool published no description. Forge does not invent one.
thrd.outbound_statusNo description publishedThis tool published no description. Forge does not invent one.
thrd.usageNo description publishedThis tool published no description. Forge does not invent one.
thrd.trust_scoreNo description publishedThis tool published no description. Forge does not invent one.
thrd.message_securityNo description publishedThis tool published no description. Forge does not invent one.
thrd.create_security_ackNo description publishedThis tool published no description. Forge does not invent one.
thrd.billing_checkout_selfNo description publishedThis tool published no description. Forge does not invent one.
thrd.claim_x_startNo description publishedThis tool published no description. Forge does not invent one.
thrd.claim_x_statusNo description publishedThis tool published no description. Forge does not invent one.
thrd.instant_onboardingNo description publishedThis tool published no description. Forge does not invent one.
0 of 16 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.
Expose Thrd (Agent Email) as an MCP server so AI clients can: Poll inbound email events Read threads and messages Reply and send outbound (policy-gated) Check usage, trust score, and security analysis This lives in the monorepo under . : your Thrd agent API key : for stateless mode (no session ids). Default is stateful. : if set, requires on every request Instant onboarding tool gate: If published to npm as : Add a server entry to your Claude Desktop config and point it at the stdio command.…
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.