Skip to main content
Glama
RudrenduPaul

NeuronScope MCP Server

by RudrenduPaul
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to NeuronScope MCP Server

No user-submitted related servers found.

    Related Servers

    • openinterp-mcp

      OpenInterpretability
      A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for mechanistic interpretability research, enabling agents to drive probe-causality and SAE-feature experiments via 8 typed tools on user's own compute (Colab).
      Apache 2.0

    • chuk-mcp-lazarus

      chrishayuk
      A
      license
      Not graded
      quality
      C
      maintenance
      Mechanistic interpretability MCP server wrapping chuk-lazarus, enabling model loading, activation extraction, probe training, steering, and ablation via MCP tools.
      21
      Apache 2.0

    • probe-mcp

      jaykobdetar
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables controlled access to language model internals via MCP, including activation capture, patching, ablation, steering, probe fitting, and bounded generation, with a persistent experiment ledger and human-approved compute.
      1
      MIT

    • mcp-context-inspector

      sohaibsohail98
      A
      license
      A
      quality
      A
      maintenance
      An MCP server that records agent execution metrics and exposes a Context Window Explorer to visualize exactly what entered the model's context window across sessions, tokens, and tool calls.
      8
      3
      MIT

    • Kodama MCP

      krazke
      -
      license
      Not graded
      quality
      Not graded
      maintenance
      AST-aware code exploration MCP server for AI agents, optimized for token efficiency.
      -
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.9/5.0

    Scored across 4 tools

    Disambiguation4/5

    Each tool targets a distinct level of analysis: trace gives correlational top-k attribution, activations provides raw per-layer stats, patch tests a single causal intervention, and circuit automates multi-component causal testing. The only real overlap is trace vs. circuit, but their descriptions clearly differentiate correlational vs. causal use cases.

    Naming Consistency5/5

    All four tool names are single lowercase words (trace, activations, patch, circuit) with no underscores, camelCase, or prefixes. Though they mix verbs and nouns, the naming convention is perfectly uniform and predictable.

    Tool Count5/5

    With exactly 4 tools, the server is well-scoped for a mechanistic interpretability toolkit. Each tool covers a distinct need: quick inspection, raw data, single-component ablation, and automated circuit discovery, without bloat or excessive specialization.

    Completeness5/5

    The tool surface covers the full interpretability workflow: ask 'why' (trace), get detailed activations (activations), test a specific hypothesis (patch), and run a broader causal analysis (circuit). No obvious gaps like model listing or arbitrary patching are necessary for the stated purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources