Loading ToolBench
A universal multi-bridge MCP hub — connect any LLM to n8n, Blender, Notion and more through a single pedagogical gateway.
polybridge-mcp has 17 tools with complete input schemas and descriptions, but quality is inconsistent. Naming follows verb_noun convention well (blender_create_object, fs_read_file, n8n_execute_workflow). Descriptions are present but often generic (avg ~80 chars, below the 194-char baseline). Parameters have types and enums where appropriate, but lack depth on constraints, ranges, and error recovery. Output schemas are not documented, LLMs cannot predict response structure. Error handling is minimal; no recovery guidance. Security concerns: fs_write_file and fs_delete_file expose filesystem operations without visible permission gates or path validation. blender_execute_script accepts arbitrary Python, a severe injection risk. No tool annotations (readOnlyHint, destructiveHint) despite clear risk levels assigned.
Apply a material (color and basic surface properties) to an existing object.
Create a new 3D object in the current Blender scene.
Execute an arbitrary Blender Python script. Use for advanced operations not covered by other tools.
Return a list of all objects currently in the Blender scene.
Render the current Blender scene and return the result as a base64 PNG image.
Delete a file. This action is irreversible.
blender_execute_script accepts arbitrary Python code with no validation, sanitization, or sandboxing. This is a critical code injection vector.
Filesystem tools (fs_write_file, fs_delete_file) lack visible permission checks and path traversal validation. No evidence of allowlist enforcement despite description claiming 'allowed directories'.
No output schemas documented for any tool. LLMs cannot predict response structure, forcing them to guess field names and types for downstream tool chaining.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 66 | <=2025-11-25 | v2 |
List all files and subdirectories inside a directory.
Read the contents of a file. Only files inside the configured allowed directories can be read.
Write content to a file. Creates the file if it does not exist, overwrites if it does.
Enable or disable an n8n workflow.
Execute a specific n8n workflow by its ID. Optionally pass input data to the workflow.
Get the result and status of a workflow execution by its execution ID.
List all workflows in the n8n instance with their names, IDs, and active status.
Append a text paragraph to an existing Notion page.
Create a new Notion page inside a parent page or database.
Read the title and text content of a Notion page.
List all available bridges and their connection status.
Tool descriptions are generic and lack context on when to use each tool vs. similar alternatives. E.g., 'Apply a material' does not explain when to call this vs. other rendering options.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk levels assigned (WRITE, DESTRUCTIVE, IRREVERSIBLE). LLMs cannot infer safety properties.