// SCAN REPORT

Engineering MCP Server

72 tools. 33 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

33 can modify or destroy data
39 read-only
72 tools total

Community server · catalogue entry verified 12/06/2026

How to control Engineering MCP Server ↓

TOOL MAP

What Engineering MCP Server exposes to your agents

Read (39) Write / Execute (32) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Engineering MCP Server tools

Destructive · High layout_delete The tool permanently removes a layout object from persistent storage with no undo or recovery mechanism implied. Execute · High model_batch_apply The tool executes multiple operations in a single call. Execute · Medium rules_apply This tool does more than read; it executes validation logic and optionally applies automatic corrections (writes/modifies data). Execute · Medium layout_compute This tool runs an external computation (ELK layout engine) on a model to produce routing results.

33 of Engineering MCP Server's 72 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Engineering MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Engineering MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "layout_delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "area_deploy": {
    "limits": [
      {
        "counter": "area_deploy_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "sfiles_parse_and_validate": {
    "limits": [
      {
        "counter": "sfiles_parse_and_validate_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Engineering MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON ENGINEERING →

Free to start. No card required.

FULL CATALOGUE

All 72 Engineering MCP Server tools

DESTRUCTIVE 1 tools
Destructive layout_delete Delete a layout from the store
EXECUTE 3 tools
Execute layout_compute Compute layout for a model using ELK. Produces orthogonal edge routing suitable for P&ID diagrams. Execute model_batch_apply Execute multiple operations in a single call for efficiency Execute rules_apply Apply validation rules and return structured issues for LLM processing. Optionally auto-fix issues.
WRITE 29 tools
Write area_deploy Deploy a template into a model (STRATEGIC operation - replaces 50+ atomic calls) Write model_tx_begin Start a transaction on a model for atomic multi-operation changes Write model_combine Merge multiple DEXPI models into one combined model. Combines all tagged plant items, instrumentation, and pip Write model_load Import a model from various formats (JSON, Proteus XML, SFILES string) - Replaces dexpi_import_json, dexpi_imp Write project_init Initialize a new git-tracked project for engineering models Write sfiles_generalize [Available via model_tx_apply or direct call] Generalize SFILES flowsheet by removing unit numbers for pattern Write bfd_to_pfd_plan Generate PFD expansion options for a BFD block. Write dexpi_add_control_loop [Available via model_tx_apply or direct call] Add complete control loop with signal generating, control, and a Write dexpi_connect_components [Available via model_tx_apply or direct call] Create piping connections between equipment and instruments. See Write dexpi_convert_from_sfiles [Available via model_tx_apply or direct call] Convert SFILES flowsheet to DEXPI P&ID model. See docs/FEATURE_P Write dexpi_create_pid [Consolidated into model_create] Initialize a new DEXPI P&ID model with metadata. See docs/FEATURE_PARITY_MATR Write dexpi_import_json [Consolidated into model_load] Import P&ID model from JSON. See docs/FEATURE_PARITY_MATRIX.md for migration gu Write dexpi_import_proteus_xml [Consolidated into model_load] Import P&ID model from Proteus 4.2 XML file. See docs/FEATURE_PARITY_MATRIX.md Write graph_connect Smart autowiring with patterns and optional inline components Write graph_modify Apply tactical graph modifications (10 actions: insert/update/remove component, inline insertion, segment oper Write layout_save_to_file Save layout to project file for persistence Write layout_update Update an existing layout with optimistic concurrency control. Requires etag to prevent concurrent modificatio Write model_create Create a new model (DEXPI P&ID or SFILES flowsheet) - Replaces dexpi_create_pid and sfiles_create_flowsheet Write model_save Export a model to various formats (JSON, GraphML, SFILES string) - Replaces dexpi_export_json, dexpi_export_gr Write model_tx_apply Apply one or more operations within an active transaction - Uses operation registry for type-safe dispatch Write model_tx_commit Commit or rollback a transaction - Returns diff and validation summary Write project_save Save a model to a git project with version control Write sfiles_add_control [Available via model_tx_apply or direct call] Add control instrumentation to flowsheet. See docs/FEATURE_PARIT Write sfiles_add_stream [Available via model_tx_apply or direct call] Add a stream connecting two units. See docs/FEATURE_PARITY_MATRI Write sfiles_add_unit [Available via model_tx_apply or direct call] Add a unit operation to the flowsheet. See docs/FEATURE_PARITY_M Write sfiles_convert_from_dexpi [Available via model_tx_apply or direct call] Convert DEXPI P&ID model to SFILES flowsheet. See docs/FEATURE_P Write sfiles_create_flowsheet [Consolidated into model_create] Initialize a new flowsheet for BFD or PFD. See docs/FEATURE_PARITY_MATRIX.md Write sfiles_export_graphml [Consolidated into model_save] Export flowsheet topology as GraphML. See docs/FEATURE_PARITY_MATRIX.md for mig Write sfiles_from_string [Consolidated into model_load] Create flowsheet from SFILES string. See docs/FEATURE_PARITY_MATRIX.md for migr
READ 39 tools
Read sfiles_parse_and_validate [Available via model_tx_apply or direct call] Parse SFILES string and validate against regex patterns. See doc Read dexpi_validate_model [Available via model_tx_apply or direct call] Validate P&ID for engineering rules and referential integrity. N Read graph_analyze_topology Analyze graph topology including paths, cycles, bottlenecks, and connectivity Read graph_calculate_metrics Calculate graph metrics like diameter, density, clustering coefficient Read graph_compare_models Compare graph structures of two models Read graph_detect_patterns Detect common patterns like heat integration, recycle loops, parallel trains Read graph_find_paths Find paths between nodes in the graph Read layout_get Get a stored layout by ID Read layout_list List layouts, optionally filtered by model Read layout_load_from_file Load layout from project file into store Read layout_validate Validate a layout against its schema and optionally check consistency with source model. Read project_list List all models in a project Read project_load Load a model from a git project Read query_model_statistics [DEPRECATED] Get statistical summary of model contents. Use search_execute(query_type= Read schema_describe_class [DEPRECATED] Get detailed information about a specific class including attributes, methods, and inheritance. U Read schema_find_class [DEPRECATED] Search for classes by partial name or pattern. Use schema_query(operation= Read schema_get_hierarchy [DEPRECATED] Get the inheritance hierarchy for a class or category. Use schema_query(operation= Read schema_list_classes [DEPRECATED] List all available classes in DEXPI or SFILES schemas. Use schema_query(operation= Read schema_query Unified schema introspection tool - consolidates all schema_ operations Read search_by_attributes [DEPRECATED] Search for components by attribute values. Use search_execute(query_type= Read search_by_stream [DEPRECATED] Search for streams by properties or connected units. Use search_execute(query_type= Read search_by_tag [DEPRECATED] Search for equipment, instruments, or nodes by tag pattern. Use search_execute(query_type= Read search_by_type [DEPRECATED] Search for components by type (e.g., all pumps, all heat exchangers). Use search_execute(query_ty Read search_connected [DEPRECATED] Find all components connected to a specific node. Use search_execute(query_type= Read search_execute Unified search tool - consolidates all search_ operations Read search_instances Find all instances of specified DEXPI class types in a model. Returns equipment inventory/search results with Read sfiles_canonical_form [Available via model_tx_apply or direct call] Convert SFILES string to canonical form for comparison. See docs Read sfiles_pattern_helper Get SFILES regex patterns and syntax examples Read sfiles_to_string [Consolidated into model_save] Convert flowsheet to compact SFILES string format. See docs/FEATURE_PARITY_MATR Read sfiles_visualize Generate visualization of SFILES flowsheet with optional stream/unit tables. Returns HTML (interactive), SVG ( Read template_get_schema Get parameter schema and metadata for a template Read template_list List available templates from the library Read validate_model Run comprehensive validation on a model. NOTE: Read validate_round_trip Validate round-trip conversion integrity Read visualize_list_renderers List available visualization renderers and their capabilities Read visualize_model Generate visualization of a model. Routes to appropriate renderer based on format and availability. Returns HT Read dexpi_export_graphml [Consolidated into model_save] Export P&ID topology as machine-readable GraphML. See docs/FEATURE_PARITY_MATRI Read dexpi_export_json [Consolidated into model_save] Export P&ID model as JSON. See docs/FEATURE_PARITY_MATRIX.md for migration guid Read sfiles_export_networkx Export flowsheet as NetworkX graph JSON
EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Sperax Ecosystem Crypto & DeFI MCP Server 1318 tools
adminautomation
Mcp Afip 1300 tools
adminautomation
Mcp Ap2 1300 tools
adminautomation
BNB Chain MCP 1240 tools
adminautomation
Nodebench 824 tools
adminautomation
Amazon Bedrock Knowledge Base Retrieval MCP Server 805 tools
adminautomation
Amazon Data Processing MCP Server 805 tools
adminautomation
Amazon ECS MCP Server 805 tools
adminautomation
FAQ

Questions about Engineering MCP Server

Can an AI agent delete data through the Engineering MCP Server MCP server? +

Yes. The Engineering MCP Server server exposes 1 destructive tools including layout_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Engineering MCP Server? +

The Engineering MCP Server server has 29 write tools including area_deploy, model_tx_begin, model_combine. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Engineering MCP Server.

How many tools does the Engineering MCP Server MCP server expose? +

72 tools across 4 categories: Destructive, Execute, Read, Write. 39 are read-only. 33 can modify, create, or delete data.

How do I enforce a policy on Engineering MCP Server? +

Register the Engineering MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Engineering MCP Server tool call.

Deterministic rules across all 72 Engineering MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ENGINEERING →

Free to start. No card required.

72 Engineering MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.