Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

McpHub

NUGET · MCPHUB · SCANNED AUG 17

MCP bridge that folds multiple MCP servers' capabilities into a few fixed tools for AI tools.

Available components

+6 this week 70 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability81
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 859 tokens (~122/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

nuget · McpHub

# add to Claude Code
claude mcp add john0king-mcphub -- dnx McpHub@0.0.1.1 --yes
# add to Codex CLI
codex mcp add john0king-mcphub -- dnx McpHub@0.0.1.1 --yes
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "john0king-mcphub": {
      "type": "local",
      "command": [
        "dnx",
        "McpHub@0.0.1.1",
        "--yes"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  john0king-mcphub:
    command: "dnx"
    args: ["McpHub@0.0.1.1", "--yes"]
// mcp.json
{
  "mcpServers": {
    "john0king-mcphub": {
      "command": "dnx",
      "args": [
        "McpHub@0.0.1.1",
        "--yes"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 14 Aug 26 0
    • Security disclosure: unverified → fail functional
  • 13 Aug 26 +5
    • Source repository: fail → pass security
  • 11 Aug 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 10 Aug 26 64

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 17 Aug 2026 · Analysed nuget/McpHub@0.0.1.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem nuget
Reason Signature present, unreadable
Dependencies 0 packages
Packages resolved 0
Tree resolution Complete
MCP tools · 7 exposed · ~762 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
add_mcp_server_config ~185

Add a new MCP server config source at runtime. You can either provide a file path to a JSON config file (which will be watched for changes), or provide inline JSON content with a 'servers' or 'mcpServers' key. Returns the created source's Id and the servers it registered. The new servers will be lazily connected on first use.

NameTypeReqDescription
filestring|nullA file path to a JSON config file (relative paths resolved against the workspace). Mutually exclusive with 'json'.
jsonstring|nullInline JSON content with a 'servers' or 'mcpServers' key, e.g. {"servers":{"myserver":{"command":"node","args":["server.js"]}}}. Mutually exclusive with 'file'.
namestring|nullOptional label for an inline source (ignored if 'file' is provided).

No output schema declared.

No examples provided.

call_mcp_capability ~129

Invoke a specific capability (tool/prompt/resource). Prerequisites: first call list_mcp_capabilities to find the qualified name, then call describe_mcp_capability to learn the required arguments and their types. Pass the qualified name "serverName.capabilityName" (or a resource URI) and arguments as a key-value object.

NameTypeReqDescription
argumentsobject|nullArguments to pass to the capability (key-value object). Optional for capabilities that take no arguments.
namestringyesThe qualified name of the capability (serverName.capabilityName) or a resource URI

No output schema declared.

No examples provided.

describe_mcp_capability ~97

Get the full details of a specific capability, including its input/output JSON schema, argument names/descriptions/required flags, etc. ALWAYS call this BEFORE call_mcp_capability to learn what arguments the capability expects. Provide the qualified name (from list_mcp_capabilities) in the format "serverName.capabilityName".

NameTypeReqDescription
namestringyesThe qualified name of the capability, format: serverName.capabilityName

No output schema declared.

No examples provided.

list_mcp_capabilities ~114

List all available capabilities (tools/prompts/resources) from all upstream MCP servers, returning a CSV table with Kind, QualifiedName, Server, Name, Description, etc. Also shows each server's connection status. This is the FIRST step: use this to discover capabilities, then call describe_mcp_capability to get parameter details before calling call_mcp_capability.

NameTypeReqDescription
kindstring|nullOptional filter by capability kind: "tool", "prompt", "resource". If omitted, all kinds are returned.

No output schema declared.

No examples provided.

list_mcp_server_configs ~60

List all registered MCP server config sources and their server definitions. Returns each source's Id, name, kind (file/inline), and the list of server configs it provides. Use this to discover source IDs needed for remove_mcp_server_config.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

remove_mcp_server_config ~89

Remove an MCP server config source by its Id. This stops the source's file watcher (if any) and disconnects all servers provided by that source. Use list_mcp_server_configs to find the source Id. Returns the removal result including which servers were disconnected.

NameTypeReqDescription
source_idstringyesThe Id of the config source to remove (obtain from list_mcp_server_configs).

No output schema declared.

No examples provided.

restart_mcp_server ~88

Restart a specific upstream MCP server by name. Use this when a server becomes unresponsive, returns errors, or needs to pick up changes. The server will be disconnected and re-connected with the same configuration.

NameTypeReqDescription
server_namestringyesThe name of the upstream MCP server to restart (the server name prefix in qualified names, e.g. "filesystem" in "filesystem.read_file")

No output schema declared.

No examples provided.