C-

npm:@goldhold/mcp-server

https://www.npmjs.com/package/@goldhold/mcp-server
72/100 · MCP Trust Grade · checked 2h ago · MCP 1.6.0

What it offers — 30 tools · Developer Tools

goldhold_search

Semantic search across GoldHold memory. Returns ranked results from past sessions.

goldhold_store

Save a memory to GoldHold. Stored via relay and synced to Pinecone.

goldhold_turn

Compound: search + store + send in one call. The primary tool for most interactions.

goldhold_resume

Resume a session. Returns recent context, inbox, and capability card.

goldhold_batch

Multiple operations in one request. Each op has a method and params.

goldhold_close

Graceful session end with summary. Saves state for next session.

goldhold_inbox

Check the GoldHold message inbox. Returns messages from other agents and the owner.

goldhold_send

Send a message via GoldHold messaging. Recipients: owner, guardian, or agent name.

goldhold_status

Check GoldHold connection health, sync state, and system info.

goldhold_summary

Get account summary: unread messages, task counts, blocked tasks, attention flags. Use as preflight before starting work.

goldhold_preflight

Standard session preflight: returns account summary + restored context in one call. Use this as the first call in any new session.

goldhold_classify

Classify intent and resolve scope for a query. Returns intent type, confidence, scope, and reasoning. Useful for debugging hook behavior.

goldhold_discover

List agents, channels, and capabilities in the GoldHold network.

goldhold_agents

List all agents in the GoldHold network.

goldhold_memory_read

Read a specific memory packet by ID, or browse a folder

goldhold_memory_namespaces

List all memory folders and their stats (count, last updated).

goldhold_task_list

List open tasks from the GoldHold task queue.

goldhold_task_create

Create a new task in the GoldHold task queue.

+12 more tools

Spec / packaging20%100
Security (OWASP MCP)30%25
Maintenance / popularity20%100
Tool hygiene15%70
Transparency / provenance15%90

Findings

WARNMCP08 References sensitive file paths / environment secrets.
INFO Static analysis of npm package @goldhold/mcp-server@1.6.0 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.
Grade another server

We re-grade npm:@goldhold/mcp-server on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:@goldhold/mcp-server grade C-
Share on X Open card image

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

MCP Trust Grade C- · wmcp.sh
[![MCP Trust Grade C-](https://wmcp.sh/mcp/grade/npm%3A%40goldhold%2Fmcp-server/badge.svg)](https://wmcp.sh/mcp/grade/npm%3A%40goldhold%2Fmcp-server)
<a href="https://wmcp.sh/mcp/grade/npm%3A%40goldhold%2Fmcp-server"><img src="https://wmcp.sh/mcp/grade/npm%3A%40goldhold%2Fmcp-server/badge.svg" alt="MCP Trust Grade C- · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.