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.
Build, run and analyse block-diagram simulations: PID, Bode, FFT, optimisation and code export.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_block | Add a new block to the canvas. Returns the new block ID. Inputs: type, x, y, link |
analyze_topology | Analyzes the block diagram structure: detects feedback loops, signal paths, and system order. Inputs: link |
auto_tune_pid | Automatically 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_commands | Executes 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_metrics | Calculates step response metrics from signal data: rise time, settling time, overshoot percentage, and steady-state error. Inputs: blockId, channel, setpoint, stepTime, link |
cancel_job | Cancel a running background job. Inputs: jobId |
clear_canvas | Remove all blocks and connections from the canvas. This is a destructive action that asks the user for approval in the BlockWerk tab. |
connect_blocks | Connect 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_tab | Returns 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_block | Delete 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_canvas | Returns 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_mask | Evaluates 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_simulation | Analyze 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_diagram | Exports the current canvas project as a complete BlockWerk JSON string. Inputs: link |
generate_code | Generates 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_history | Returns the list of recent canvas operations performed by the AI, showing what can be undone. |
get_analysis_measurements | Retrieves the currently active pinned measurements and their computed values across plotted signals in the Analysis panel. Inputs: blockId |
get_architect_memory | Returns the persistent memory object of the Architect. |
get_available_blocks | Returns 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_data | Computes 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_preview | Captures 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_status | Returns the simulation engine status, including supported solvers, active background jobs, and compilation/WASM capabilities. |
get_fft_data | Computes FFT (frequency spectrum) of a Scope signal. Returns frequencies and magnitudes. Inputs: blockId, channel |
get_job_status | Check the status and progress of a background job. Inputs: jobId |
get_share_link | Returns 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_data | Returns time series data from a Scope block output for analysis. Inputs: blockId, channel, link |
get_templates | Lists 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_fopdt | Analyzes 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_jobs | List all recent background jobs and their status. |
load_diagram | Atomically 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_template | Replaces 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_parameter | Optimizes 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_parameters | Finds 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_results | Stores the result of a diagram run in the BlockWerk chat view. Inputs: record |
redo_last_ai_action | Redoes the last undone canvas modification. |
run_simulation | Triggers a new simulation run with the current canvas state and settings, refreshing the signal data. Inputs: duration, sampleTime, reason, link |
start_optimization | Start a parameter optimization job in the background. Inputs: blockId, paramName, min, max, measureBlockId, setpoint |
sweep_parameter | Runs 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_layout | Automatically rearrange all blocks on the canvas into a clean, left-to-right flow. |
undo_last_ai_action | Undoes the last canvas modification made by the AI (add block, connect, delete, update parameter). |
update_architect_memory, update_params, validate_canvas, validate_engineering_units
Every block below points at https://blockwerk-mcp-worker.blockwerk.workers.dev/. Pick your client and copy.
claude mcp add --transport http blockwerk https://blockwerk-mcp-worker.blockwerk.workers.dev/
{
"mcpServers": {
"blockwerk": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://blockwerk-mcp-worker.blockwerk.workers.dev/"]
}
}
}{
"mcpServers": {
"blockwerk": {
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
}
}
}{
"servers": {
"blockwerk": {
"type": "http",
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
}
}
}{
"context_servers": {
"blockwerk": {
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
}
}
}{
"mcpServers": {
"blockwerk": {
"serverUrl": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
}
}
}{
"mcpServers": {
"blockwerk": {
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
}
}
}name: BlockWerk
version: 0.0.1
schema: v1
mcpServers:
- name: BlockWerk
type: streamable-http
url: https://blockwerk-mcp-worker.blockwerk.workers.dev/{
"mcpServers": {
"blockwerk": {
"httpUrl": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
}
}
}{
"mcpServers": {
"blockwerk": {
"type": "http",
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
}
}
}{
"mcpServers": {
"blockwerk": {
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev/"
}
}
}goose://extension?url=https%3A%2F%2Fblockwerk-mcp-worker.blockwerk.workers.dev%2F&type=streamable_http&id=blockwerk&name=BlockWerk
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.
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.
It answered our last check on 22 November 2026 in 316 ms. Over 4 checks since 6 October 2026 it answered 4.
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.
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.
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.