Qiao-MCP
Enables AI assistants to interact with bridge structural analysis software for modeling, construction stages, and code checking.
README
š Qiao-MCP
<!-- mcp-name: io.github.SorataYang/qiao-mcp -->
English Ā· ē®ä½äøę
Full-lifecycle bridge structural analysis ā modeling, staging, code checks
ꔄę¢å ØčæēØē»ęåę MCP ęå”åØ ā 建樔ćę½å·„é¶ę®µćč§čéŖē®
Qiao-MCP is a Model Context Protocol (MCP) server that enables AI assistants to interact with bridge structural analysis software. It provides tools for creating bridge models, applying loads, running structural analysis, and reviewing results.
Features
š§ Tools (132 tools, grouped)
Tools are organized by workflow area. Highlights per group:
| Group | Representative tools |
|---|---|
| Core modeling | create_nodes_linear, create_beam_elements_linear, create_material, create_section (all parametric section types), create_polygon_section |
| Loads | create_load_group, create_load_case, set_self_weight_stage, set_gravity, apply_nodal_force, apply_beam_distributed_load, temperature/settlement loads |
| Boundary | set_support, add_elastic_link, add_master_slave_link, add_elastic_support, add_beam_constraint |
| Groups | create_structure_group, add_to_structure_group, merge_operation_stage |
| Stages & analysis | add_construction_stage, merge_operation_stage, configure_analysis, run_analysis (async, progress-reporting), get_analysis_results |
| Tendons | create_tendon_property, create_tendon_2d, apply_prestress, get_tendon_info |
| Traffic (moving load) | add_node_tandem, add_influence_plane, add_traffic_lane, add_standard_vehicle, create_live_load_case |
| Checking | setup_concrete_check, add_check_load_combination, add_parametric_reinforcement, run_concrete_check, get_check_data |
| Queries | get_model_info, get_model_data (by kind), find_entities, calc_section_property, get_special_results (paginated where applicable) |
| Modification | initialize_model, save_model_file, open_model_file, update_node, move_nodes, update_element, remove_nodes, remove_elements |
| Visualization | save_model_screenshot, plot_analysis_result (optionally return viewable images), set_view_angle, display_ids |
| Workflows | create_simple_beam_bridge, create_continuous_beam_bridge |
| Gateway & diagnostics | check_qiaotong_connection, list_qtmodel_api, call_qtmodel_api ā diagnose the bridge connection or discover and call long-tail qtmodel methods with signature validation |
Tool responses are normalized to structured content ({status, ...}), while image
tools can return MCP image content directly. Tool failures use typed MCP errors, and
read-only, destructive, and open-world operations carry MCP tool annotations. The
server instructions include the full tool-group overview; use list_qtmodel_api
before calling an uncovered backend method through the gateway.
š¦ Resources (7 resources)
| URI | Description |
|---|---|
bridge://model/summary |
Model overview |
bridge://model/materials |
Material list |
bridge://model/sections |
Section list |
bridge://model/load-cases |
Load cases |
bridge://model/stages |
Construction stages |
bridge://model/structure-groups |
Structure groups |
bridge://model/boundaries |
Boundary conditions |
š¬ Prompts (4 workflows)
| Prompt | Description |
|---|---|
design-simple-beam |
Simple beam bridge design workflow (ē®ęÆę¢č®¾č®”) |
design-continuous-beam |
Continuous beam bridge design (čæē»ę¢č®¾č®”) |
check-structure |
Structural code checking (ē»ęę£ē®) |
construction-stage-analysis |
Construction stage analysis (ę½å·„é¶ę®µåę) |
Architecture
qiao-mcp/
āāā src/qiao_mcp/
ā āāā server.py # MCP server entry point
ā āāā tools/ # MCP Tools (envelope-wrapped)
ā āāā resources/ # MCP Resources
ā āāā prompts/ # MCP Prompts
ā āāā providers/ # Backend adapters
ā āāā __init__.py # BridgeProvider abstract base
ā āāā qtmodel_provider.py # QiaoTong adapter
āāā tests/ # Offline unit, integration, and API contract tests
āāā reference-docs/ # Review notes and project documentation
The Provider pattern keeps the 132 tools decoupled from any single backend. Select one with
BRIDGE_PROVIDER; each provider declares its own software-specific rules, so the LLM adapts
without prompt changes. Currently supports:
- QTModel (
qtmodel, default) ā QiaoTong (ꔄé) bridge analysis software (user manual)
Adding a backend means implementing BridgeProvider and registering one line ā no tool-layer
changes. See Backend Selection.
Quick Start
Prerequisites
- Python >= 3.11
- uv package manager
qtmodel2.6.3 (installed byuv sync)- QiaoTong software 2.6.3 running when calling backend model, analysis, or visualization operations
The MCP server can start without QiaoTong. Use check_qiaotong_connection to
distinguish a connected server, a version mismatch, and software that is not running.
Install & Run
# Install dependencies
uv sync
# Run the server
uv run qiao-mcp
Configure in Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"qiao-mcp": {
"command": "uv",
"args": ["--directory", "/path/to/qiao-mcp", "run", "qiao-mcp"]
}
}
}
Configure in Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"qiao-mcp": {
"command": "uv",
"args": ["--directory", "/path/to/qiao-mcp", "run", "qiao-mcp"]
}
}
}
Configure in Reasonix (UI)
Open Settings ā MCP & Tools, then add a new MCP server:
- Name:
qiao-mcp - Transport:
stdio(keep default) - Command:
uv --directory /path/to/qiao-mcp run qiao-mcp- Replace
/path/to/qiao-mcpwith your actual project path - Windows: use backslashes
D:\path\to\qiao-mcp - macOS/Linux: use forward slashes
/path/to/qiao-mcp
- Replace
- Environment (optional):
UV_PYTHON=3.11
Click Add to save.
Configure in Cherry Studio (UI)
Open 设置 ā ę©å± ā MCP Servers, then add a new server:
- åē§° (Name):
qiao-mcp - ęčæ° (Description): Optional description
- ē±»å (Type):
ę åč¾å „ / č¾åŗ (stdio) - å½ä»¤ (Command):
uv - å
ē®”ēåØ (Package Manager): Select
é»č®¤(Default) - åę° (Args):
(Each line is one argument, no/path/to/qiao-mcp run qiao-mcp--directoryprefix needed)- Replace
/path/to/qiao-mcpwith your actual project path
- Replace
Click äæå to save.
Test with MCP Inspector
npx @modelcontextprotocol/inspector uv run qiao-mcp
LAN debugging proxy
For cross-machine debugging, scripts/qiaotong_lan_proxy.py
forwards a LAN-facing port to the QiaoTong API on the same machine. It uses
45125 for the proxy and forwards to the selected QiaoTong process on
127.0.0.1:55125:
python scripts/qiaotong_lan_proxy.py
Then point the client machine at:
from qtmodel import mdb
mdb.set_url("http://<proxy-machine-LAN-IP>:45125/pythonForQt/")
The proxy prints each forwarded request and response. When several QiaoTong
processes are running, keep one process on 55125 for this fixed proxy, or use
separate proxy instances and ports for separate processes.
An SSH tunnel is an alternative that does not expose the API port on the LAN:
ssh -N -L 45125:127.0.0.1:55125 <user>@<qiaotong-machine-LAN-IP>
Use http://127.0.0.1:45125/pythonForQt/ in the client machine while the tunnel
is running.
Development
# Install in dev mode (includes ruff, mypy, pytest)
uv sync
# Run directly
uv run python -m qiao_mcp.server
# Quality gate (same checks as CI)
uv run ruff check src/ tests/
uv run mypy src/qiao_mcp/
uv run pytest tests/ -q
The test suite is designed to run offline ā it does not require the QiaoTong software.
Provider/tool calls are validated against the installed qtmodel API signatures
(contract tests) and dispatched against an in-process fake backend.
Backend: QTModel (ꔄé)
This MCP server wraps the qtmodel Python API which provides access to:
- mdb ā Model database: building & modifying bridge models
- odb ā Output database: querying analysis results & visualization
- cdb ā Check database: structural verification & code checking
Versioning
Qiao-MCP versions independently from qtmodel ā the project iterates on its own
(bug fixes, new tools, docs) without waiting for a backend release, and a backend
release does not force a version bump here. The backend requirement is expressed
where it belongs: in the dependency constraint.
Compatibility
| Qiao-MCP | qtmodel | QiaoTong software |
|---|---|---|
| 0.3.x | 2.6.3 ā 2.6.x | 2.6.3 |
| 0.2.x | 2.5.0 ā 2.5.x | 2.5.0 |
The QiaoTong software API version and the installed qtmodel must match
exactly ā qtmodel 2.6+ performs a precise version handshake and refuses to
connect otherwise. Run check_qiaotong_connection to see both versions and what
to do when they differ.
0.x signals the API is still free to change; it is not a statement about
release quality. When moving to a new qtmodel minor line, raise the dependency
bound and add a row to the table above.
License
Copyright 2026 Sorata (https://github.com/SorataYang)
Licensed under the Apache License, Version 2.0. See LICENSE. Additional attribution notices are available in NOTICE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.