Developer Tools
blockwerk.tech
Provides tools to inspect, add, connect, and configure blocks on a visual canvas for building node-based workflows.
ENDPOINT 1
https://blockwerk-mcp-worker.blockwerk.workers.dev
MCP server metadata
- Name
- blockwerk-mcp
- Version
- 1.0.0
BlockWerk is a visual block-diagram simulation canvas. These tools drive a live blockwerk.tech browser tab over a relay. PAIRING: when a blockwerk.tech tab is paired, every tool drives that live canvas. When none is paired, the remote server still answers on its own: you can browse the block library, build and edit a diagram, inspect it, export it, and call get_share_link. Tools that need the browser (run_simulation and everything reading its results, optimisation, and jobs) require a pairing — when unpaired those return the same share link; give it to the user and ask them to open it and press Run. SHARING: get_share_link works either way and carries the whole project inside the URL. Offer it whenever the user wants to see, keep or hand off what you built. BUILD A DIAGRAM — preferred path: - For a classic system (PID loop, cruise control, inverted pendulum, a filter, a rectifier), call get_templates FIRST. These diagrams are verified and already run, so load_template removes the guessing about block types, port ids and gains entirely. Both work with or without a paired tab. - For a whole diagram in one shot, use load_diagram. It is the fastest and most reliable. Each connection MUST include a unique "id" field; omitting it fails. - For incremental edits, use: get_available_blocks (discover types + port ids) -> add_block -> connect_blocks -> run_simulation. - Parameter keys are normalized automatically: standard mathematical notation (Kp/Ki/Kd/N, frequency, lower/upper, duty_cycle) works for both add_block inline params and update_params. - Never guess block types or port ids — read get_available_blocks first. READING RESULTS (ground truth): - After run_simulation, read get_signal_data for actual values. Scope and Sink blocks automatically trace connected upstream source signals. - Inspect canvas state with describe_canvas / analyze_topology rather than assuming. CODE GENERATION: - To export standalone production code (C++/Arduino, Python, Safe Rust) from any canvas diagram, use generate_code. Use InPort and OutPort blocks to define explicit external hardware I/O interfaces. APPROVALS: clear_canvas, delete_block, load_diagram and load_template ask the user for an in-tab approval click. Use them deliberately; prefer one load_diagram over many destructive calls.
Known tools 42
describe_canvasReturns a structured description of all blocks and connections currently on the canvas.
Inferred read-onlyget_available_blocksReturns the block types in the library with their descriptions, configurable parameters, and exact input/output port IDs.
Inferred read-onlyload_diagramAtomically replaces the entire canvas with a complete diagram defined as a BlockWerk project JSON string.
Inferred read-onlyexport_diagramExports the current canvas project as a complete BlockWerk JSON string.
Inferred read-onlyget_share_linkReturns a link that opens the current diagram on the BlockWerk canvas.
Inferred read-onlytidy_layoutAutomatically rearrange all blocks on the canvas into a clean, left-to-right flow.
Inferred read-onlybatch_commandsExecutes multiple canvas manipulation and background job commands in a single round-trip.
Inferred read-onlyanalyze_topologyAnalyzes the block diagram structure: detects feedback loops, signal paths, and system order.
Inferred read-onlycalculate_metricsCalculates step response metrics from signal data: rise time, settling time, overshoot percentage, and steady-state error.
Inferred read-onlyget_analysis_measurementsRetrieves the currently active pinned measurements and their computed values across plotted signals in the Analysis panel.
Inferred read-onlyevaluate_spec_maskEvaluates signal data against automated design specifications and tolerance corridors (rise time, settling time, overshoot %, steady-state error, min/max limits).
Inferred read-onlyvalidate_engineering_unitsChecks the consistency of engineering units across the diagram.
Inferred read-onlyvalidate_canvasPerforms pre-flight topological and numerical integrity checks on the canvas.
Inferred read-onlyget_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.
Potential side effectsget_templatesLists the built-in, verified BlockWerk diagrams: classic control systems (PID loop, cruise control, inverted pendulum), signal processing, electrical and physics models.
Inferred read-onlyload_templateReplaces the entire canvas with one of the built-in verified diagrams, by id from get_templates.
Inferred read-onlyrun_simulationTriggers a new simulation run with the current canvas state and settings, refreshing the signal data.
Inferred read-onlysweep_parameterRuns simulations across a list of values for one parameter, returning control quality metrics (IAE, overshoot, settling_time, steady_state_error) per value.
Inferred read-onlyoptimize_parametersFinds the optimal value for a single parameter using golden-section search.
Inferred read-onlyoptimize_multi_parameterOptimizes 2–6 parameters simultaneously using Nelder-Mead simplex search, for example Kp, Ki and Kd of a PID controller at once.
Inferred read-onlyauto_tune_pidAutomatically tunes a PID controller using the Ziegler-Nichols ultimate cycle method.
Inferred read-onlyidentify_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).
Inferred read-onlyexplain_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.
Inferred read-onlyget_bode_dataComputes magnitude and phase frequency response (Bode data) between two blocks.
Inferred read-onlyget_engine_statusReturns the simulation engine status, including supported solvers, active background jobs, and compilation/WASM capabilities.
Inferred read-onlygenerate_codeGenerates standalone production code (C++, Python, Rust) from the current canvas diagram.
Inferred read-onlyundo_last_ai_actionUndoes the last canvas modification made by the AI (add block, connect, delete, update parameter).
Potential side effectsget_ai_historyReturns the list of recent canvas operations performed by the AI, showing what can be undone.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.blockwerk-mcp]
url = "https://blockwerk-mcp-worker.blockwerk.workers.dev"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"blockwerk-mcp": {
"type": "http",
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: blockwerk-mcp
Remote MCP URL: https://blockwerk-mcp-worker.blockwerk.workers.dev
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"blockwerk-mcp": {
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"blockwerk-mcp": {
"type": "http",
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "blockwerk-mcp",
"transport": "streamable-http",
"url": "https://blockwerk-mcp-worker.blockwerk.workers.dev"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for workers.dev was fetched 2026-09-25T13:56:19.197Z.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.