McpHub
NUGET · MCPHUB · SCANNED AUG 17
MCP bridge that folds multiple MCP servers' capabilities into a few fixed tools for AI tools.
Available components
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
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 6 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
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.
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
claude mcp add john0king-mcphub -- dnx McpHub@0.0.1.1 --yes
codex mcp add john0king-mcphub -- dnx McpHub@0.0.1.1 --yes
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"john0king-mcphub": {
"type": "local",
"command": [
"dnx",
"McpHub@0.0.1.1",
"--yes"
],
"enabled": true
}
}
} mcp_servers:
john0king-mcphub:
command: "dnx"
args: ["McpHub@0.0.1.1", "--yes"] {
"mcpServers": {
"john0king-mcphub": {
"command": "dnx",
"args": [
"McpHub@0.0.1.1",
"--yes"
]
}
}
} 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.
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 |
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.
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.
| Name | Type | Req | Description |
|---|---|---|---|
| file | string|null | – | A file path to a JSON config file (relative paths resolved against the workspace). Mutually exclusive with 'json'. |
| json | string|null | – | Inline JSON content with a 'servers' or 'mcpServers' key, e.g. {"servers":{"myserver":{"command":"node","args":["server.js"]}}}. Mutually exclusive with 'file'. |
| name | string|null | – | Optional 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.
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object|null | – | Arguments to pass to the capability (key-value object). Optional for capabilities that take no arguments. |
| name | string | yes | The 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".
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | The 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.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string|null | – | Optional 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.
| Name | Type | Req | Description |
|---|---|---|---|
| source_id | string | yes | The 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.
| Name | Type | Req | Description |
|---|---|---|---|
| server_name | string | yes | The 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.