tqs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TQS_ROOT | No | Root of the building tree | none |
| TQS_PYTHON | No | Interpreter with the TQS package installed | the server's own interpreter |
| TQS_MCP_TIMEOUT | No | Default subprocess timeout in seconds | 120 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tqs_statusA | Check whether the TQS Python Interface is reachable. Reports the interpreter in use, which TQS modules import, and the TQS programs/support/user folders. Run this first when TQS tools misbehave. |
| tqs_list_buildingsA | List TQS buildings under a root folder. A building is a subfolder containing EDIFICIO.DAT. Defaults to the TQS_ROOT environment variable. |
| tqs_building_readA | Read a TQS building into JSON: project metadata, analysis model, floors, concrete strengths, covers and load cases. Pass a building folder or a path to EDIFICIO.DAT. |
| tqs_building_editA | Change building properties and save. Defaults to dry_run=true, which reports the old and new value of every change without writing. Set dry_run=false to commit; TQS keeps the prior version as EDIFICIO.BAK. |
| tqs_dwg_readA | Read a TQS drawing (.DWG): scale and system metadata, extents, levels, blocks, entity counts, and entities themselves. Filter by entity type, level, or text content — extracting TEXT entities is the usual way to pull rebar callouts and labels out of a drawing. Units are centimeters. |
| tqs_processA | Run TQS Manager processing tasks against a building (TQSExec) — global processing, drawing generation, rebar schedules. This overwrites calculation results and drawings in the building tree, and can run for many minutes. See the tqsexec reference for the task list. |
| tqs_introspectA | Inspect the installed TQS API: list a module's or object's real methods and properties with signatures. Use this whenever you are unsure a name exists — the published docs cover only part of the surface. |
| tqs_run_scriptA | Run Python with the TQS modules importable, in a separate process. The escape hatch for anything the other tools do not cover. Assign to a variable named |
| tqs_referenceA | Bundled offline reference for the TQS Python Interface. Call with no arguments to list topics. Read the relevant topic before writing TQS code with tqs_run_script. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| TQS reference: other-modules | TQS Python Interface reference — other-modules |
| TQS reference: overview | TQS Python Interface reference — overview |
| TQS reference: tqsbuild | TQS Python Interface reference — tqsbuild |
| TQS reference: tqsdwg | TQS Python Interface reference — tqsdwg |
| TQS reference: tqsexec | TQS Python Interface reference — tqsexec |
| TQS reference: tqsgrid | TQS Python Interface reference — tqsgrid |
| TQS reference: tqsutil | TQS Python Interface reference — tqsutil |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/carlostavares-manager-MNGT/tqs-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server