Index / MCP servers / BlockWerk

BlockWerk MCP server

BlockWerk is a remote MCP server that gives an AI agent 44 tools, among them add_block, analyze_topology, auto_tune_pid. It answers at https://blockwerk-mcp-worker.blockwerk.workers.dev/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 6 October 2026; the last check, on 22 November 2026, succeeded.

Status
Answering
Tools
44
Reliability
4 of 4 checks
Response time
316 ms
Transport
streamable HTTP
Last checked
22 November 2026

Build, run and analyse block-diagram simulations: PID, Bode, FFT, optimisation and code export.

Description as the publisher wrote it.

The 44 tools BlockWerk offers

ToolWhat it does
add_blockAdd a new block to the canvas. Returns the new block ID.
Inputs: type, x, y, link
analyze_topologyAnalyzes the block diagram structure: detects feedback loops, signal paths, and system order.
Inputs: link
auto_tune_pidAutomatically tunes a PID controller using the Ziegler-Nichols ultimate cycle method. Finds the ultimate gain (Ku) and oscillation period (Tu) via binary search, then applies ZN formulas. No prior knowledge of the plant required.
Inputs: pidBlockId, measureBlockId, setpoint, controlType, minGain, maxGain
batch_commandsExecutes multiple canvas manipulation and background job commands in a single round-trip. Use "handle" strings to refer to blocks added earlier in the same batch. When adding TextNote annotations, set "anchors" to the handles/IDs of the des
Inputs: commands, link
calculate_metricsCalculates step response metrics from signal data: rise time, settling time, overshoot percentage, and steady-state error.
Inputs: blockId, channel, setpoint, stepTime, link
cancel_jobCancel a running background job.
Inputs: jobId
clear_canvasRemove all blocks and connections from the canvas. This is a destructive action that asks the user for approval in the BlockWerk tab.
connect_blocksConnect an output port of one block to an input port of another. Automatically resolves common port aliases (e.g., "in" -> "signal" for uPlotDisplay, "in" -> "error" for PIDController, "+" / "-" for Subtraction).
Inputs: fromBlockId, fromPortId, toBlockId, toPortId, link
connect_browser_tabReturns a one-time link that connects this conversation to a live BlockWerk browser tab. Opening it shows the current diagram and asks the user to allow the connection; after that the tools run on that tab, including simulations and their r
Inputs: link
delete_blockDelete a block and all its connections from the canvas. This is a destructive action that asks the user for approval in the BlockWerk tab.
Inputs: blockId, link
describe_canvasReturns a structured description of all blocks and connections currently on the canvas. Set "compact" to true for a token-efficient summary.
Inputs: compact, link
evaluate_spec_maskEvaluates signal data against automated design specifications and tolerance corridors (rise time, settling time, overshoot %, steady-state error, min/max limits).
Inputs: blockId, channel, setpoint, stepTime, maxOvershootPercent, maxSettlingTime
explain_simulationAnalyze the last completed simulation and return a structured diagnosis: signal anomalies (NaN, divergence, oscillation), solver health (rejection rate, efficiency), algebraic loops, and optional stability margins. Returns JSON with severit
Inputs: stabilityMargins
export_diagramExports the current canvas project as a complete BlockWerk JSON string.
Inputs: link
generate_codeGenerates standalone production code (C++, Python, Rust) from the current canvas diagram. Returns structured code files, interfaces (inputs/outputs), execution order, and diagnostics.
Inputs: modelName, sampleTime, target, encapsulateSubsystems
get_ai_historyReturns the list of recent canvas operations performed by the AI, showing what can be undone.
get_analysis_measurementsRetrieves the currently active pinned measurements and their computed values across plotted signals in the Analysis panel.
Inputs: blockId
get_architect_memoryReturns the persistent memory object of the Architect.
get_available_blocksReturns the block types in the library with their descriptions, configurable parameters, and exact input/output port IDs. Without a filter it returns a compact list of all types; with a list of type IDs it returns full details for those typ
Inputs: filter
get_bode_dataComputes magnitude and phase frequency response (Bode data) between two blocks. Traces path backwards from outputBlockId. Returns analytic response if the path contains only linear blocks, otherwise runs numerical sweep.
Inputs: inputBlockId, outputBlockId, startFreq, endFreq, pointsPerDecade
get_canvas_previewCaptures a visual screenshot preview of the canvas branded with the official BlockWerk watermark badge and returns the live interactive URL to view and edit the diagram online.
Inputs: type
get_engine_statusReturns the simulation engine status, including supported solvers, active background jobs, and compilation/WASM capabilities.
get_fft_dataComputes FFT (frequency spectrum) of a Scope signal. Returns frequencies and magnitudes.
Inputs: blockId, channel
get_job_statusCheck the status and progress of a background job.
Inputs: jobId
get_share_linkReturns a link that opens the current diagram on the BlockWerk canvas. The whole project travels compressed inside the URL, so it needs no account and nothing is uploaded. Opening the link in a browser shows the diagram, where the simulatio
Inputs: link
get_signal_dataReturns time series data from a Scope block output for analysis.
Inputs: blockId, channel, link
get_templatesLists the built-in, verified BlockWerk diagrams: classic control systems (PID loop, cruise control, inverted pendulum), signal processing, electrical and physics models. Each entry gives an id, what the diagram does, its difficulty and the
Inputs: category, interactive
identify_fopdtAnalyzes a step response from a plant to identify its First-Order Plus Dead Time (FOPDT) parameters: Gain (K), Time Constant (tau), and Dead Time (theta). Requires a completed simulation with a step input connected to the plant. Returns the
Inputs: blockId, stepAmplitude, stepTime
list_jobsList all recent background jobs and their status.
load_diagramAtomically replaces the entire canvas with a complete diagram defined as a BlockWerk project JSON string. The JSON has a "blocks" array (each block needs a unique "id" and "type"; "x"/"y"/"params" are optional) and a "connections" array (ea
Inputs: json
load_templateReplaces the entire canvas with one of the built-in verified diagrams, by id from get_templates. The template carries its topology, parameters and simulation settings. Returns the block and connection counts, the verified simulation setting
Inputs: templateId
optimize_multi_parameterOptimizes 2–6 parameters simultaneously using Nelder-Mead simplex search, for example Kp, Ki and Kd of a PID controller at once.
Inputs: targets, measureBlockId, setpoint, objective, maxIterations
optimize_parametersFinds the optimal value for a single parameter using golden-section search. Minimizes IAE (integral absolute error), overshoot, or settling_time within a [min, max] range. Converges in about 10 simulations.
Inputs: blockId, paramName, min, max, measureBlockId, setpoint
record_view_resultsStores the result of a diagram run in the BlockWerk chat view.
Inputs: record
redo_last_ai_actionRedoes the last undone canvas modification.
run_simulationTriggers a new simulation run with the current canvas state and settings, refreshing the signal data.
Inputs: duration, sampleTime, reason, link
start_optimizationStart a parameter optimization job in the background.
Inputs: blockId, paramName, min, max, measureBlockId, setpoint
sweep_parameterRuns simulations across a list of values for one parameter, returning control quality metrics (IAE, overshoot, settling_time, steady_state_error) per value. Requires measureBlockId and setpoint.
Inputs: blockId, paramName, values, measureBlockId, setpoint
tidy_layoutAutomatically rearrange all blocks on the canvas into a clean, left-to-right flow.
undo_last_ai_actionUndoes the last canvas modification made by the AI (add block, connect, delete, update parameter).
4 more tools

update_architect_memory, update_params, validate_canvas, validate_engineering_units

Add BlockWerk to your AI client

Every block below points at https://blockwerk-mcp-worker.blockwerk.workers.dev/. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http blockwerk https://blockwerk-mcp-worker.blockwerk.workers.dev/
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "blockwerk": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://blockwerk-mcp-worker.blockwerk.workers.dev/"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "blockwerk": {
      "url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "blockwerk": {
      "type": "http",
      "url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "blockwerk": {
      "url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "blockwerk": {
      "serverUrl": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "blockwerk": {
      "url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: BlockWerk
version: 0.0.1
schema: v1
mcpServers:
  - name: BlockWerk
    type: streamable-http
    url: https://blockwerk-mcp-worker.blockwerk.workers.dev/
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "blockwerk": {
      "httpUrl": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "blockwerk": {
      "type": "http",
      "url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "blockwerk": {
      "url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fblockwerk-mcp-worker.blockwerk.workers.dev%2F&type=streamable_http&id=blockwerk&name=BlockWerk

Is BlockWerk up right now?

It answered our last check on 22 November 2026 in 316 ms. Over 4 checks since 6 October 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to BlockWerk

Questions about BlockWerk

How many tools does BlockWerk have?

44, as returned by the server's own tools/list on 22 November 2026: add_block, analyze_topology, auto_tune_pid, batch_commands, calculate_metrics, cancel_job, clear_canvas, connect_blocks, and 36 more.

Is BlockWerk down?

It answered our last check on 22 November 2026 in 316 ms. Over 4 checks since 6 October 2026 it answered 4.

How do I add BlockWerk to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://blockwerk-mcp-worker.blockwerk.workers.dev/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does BlockWerk need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: tech.blockwerk. Endpoint host: blockwerk-mcp-worker.blockwerk.workers.dev. ARD identifier: urn:air:tech.blockwerk:mcp:mcp. First indexed 6 October 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.