FastAPI Architect MCP
fastapi-architect-mcp
An MCP server that gives Claude Code IDE-level intelligence for FastAPI projects — semantic code navigation, safe renaming, route inspection, dependency trees, and Pydantic model analysis.
Instead of Claude reading files blindly, it calls structured tools backed by Jedi (Python language server) and Python's AST.
Tools
Tool | Description |
| Find all usages of a symbol across the project |
| Safely rename a symbol across all files |
| Jump to where a symbol is defined |
| Get completion suggestions at a cursor position |
| List all FastAPI routes across the entire project |
| Get the full |
| Full graph: route → input models → dependencies → response model |
| Detect routes missing a |
| List all Pydantic/SQLModel models in a file |
| Inspect a model's fields, types, defaults, and validators |
| Find everywhere a model is used across the project |
| Detect field mismatches between ORM model and Pydantic schema |
Installation
pip install fastapi-architect-mcpConfiguration
Option 1 — Global (available in all projects)
Add to ~/.claude/settings.json:
{
"mcpServers": {
"fastapi-architect": {
"command": "fastapi-architect-mcp"
}
}
}Option 2 — Per project (recommended for best results)
Create .mcp.json at your project root:
{
"mcpServers": {
"fastapi-architect": {
"command": "/path/to/your/project/venv/bin/fastapi-architect-mcp"
}
}
}Using your project's own venv gives Jedi access to all your project's dependencies, which enables full cross-file find_references and rename_symbol support.
Then restart Claude Code.
Usage examples
Once connected, you can ask Claude Code things like:
"List all routes in this project"
"What are the dependencies of the
get_usershandler?""Find all references to
get_dbacross the project""Rename
get_dbtoget_sessioneverywhere""Inspect the
UserCreatemodel""Are there any routes missing a response_model?"
"Show me the full dependency graph for the users router"
"Are there any mismatches between my
UserORM model andUserPublicschema?"
Supported patterns
Dependency injection
def handler(x=Depends(func))— standard FastAPIdef handler(*, x=Depends(func))— keyword-only args@router.get("/", dependencies=[Depends(func)])— decorator-level depsSessionDep = Annotated[Session, Depends(get_db)]— Annotated aliases (modern FastAPI)
Models
BaseModel— PydanticSQLModel— SQLModelBaseSettings— Pydantic settingsRootModel— Pydantic v2Inherited models (e.g.
class UserCreate(UserBase))
Validators
@validator— Pydantic v1@field_validator— Pydantic v2
Known limitations
find_referencesandrename_symbolwork cross-file only when the MCP is configured to use the project's own venv (Option 2 above). With a global install, they only operate on the file where the symbol is defined.get_dependenciessupports native FastAPIDepends()only. Other DI frameworks (Dishka, dependency-injector, etc.) are not supported.Runtime dependencies (middleware, lifespan events, startup hooks) are not visible to static analysis and won't appear in dependency trees.
get_completionsis most useful at attribute access positions (e.g. after a.). On empty lines it returns all Python builtins.
Requirements
Python 3.11+
Claude Code (VS Code extension or CLI)
Author
Abdessamad Touzani
GitHub: @AbdessamadTzn
LinkedIn: abdessamadtouzani
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/AbdessamadTzn/fastapi-architect-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server