Neuronscope runs on your own machine — the client starts it, so there is no endpoint to ping. 176 installs a week from pypi. Last commit 25 Aug 2026.
Traces which neurons and attention heads drive a language model's output via MCP tools.
Today is the operative word: we check Neuronscope every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add neuronscope -- uvx neuronscope-cli
{
"mcpServers": {
"neuronscope": {
"args": [
"neuronscope-cli"
],
"command": "uvx"
}
}
}
[mcp_servers.neuronscope]
command = "uvx"
args = ["neuronscope-cli"]
{
"mcpServers": {
"neuronscope": {
"args": [
"neuronscope-cli"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"neuronscope": {
"args": [
"neuronscope-cli"
],
"command": "uvx"
}
}
}
Invoicing you drive by talking to your AI: log time, raise invoices and track what's owed via MCP.
MCP tools for UVM/cocotb logs, coverage, regressions, and waveform triage.
MCP server for Altmetric APIs - track research attention across news, policy, social media, and more
CognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.
VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools.
TRACE32 CMM LSP via MCP — parse, diagnostics, completions, hover, symbols
MCP server for Langfuse LLM observability — trace and observation analysis.
SpiderIQ Gate: SpiderGate LLM gateway (completions, models, usage, traces)
Answers built from our own checks of this server.