Debugforge
UnclaimedDebugForge — MCP server that connects Lauterbach TRACE32 debuggers to AI agents for autonomous debugging.
Set up this server
01 / Choose your client
02 / Before you connect
Authentication is not specified. Check the project instructions before connecting.
Project instructions03 / Add the configuration
claude mcp add --transport stdio 'debugforge' -- 'uvx' 'debugforge'04 / Check it in your client
Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
40 of 40 tools
Documented tools (40)
From project documentation. A server handshake does not verify each tool’s description or behavior.
clear_all_breakpoints
Delete all breakpoints at once
connect
Connect to a TRACE32 PowerView instance
delete_breakpoint
Delete a breakpoint
disconnect
Disconnect from TRACE32
evaluate
Evaluate a TRACE32 expression or function
execute_command
Execute any TRACE32 PRACTICE command
get_callstack
Get call stack with function names
get_current_function
Get name of currently executing function
get_locals
Get call stack with all local variables per frame
get_project_config
Get the loaded project configuration (paths, scripts, settings)
get_run_stats
Combined run/halt statistics
get_source_location
Get current source file and line
get_state
Get current CPU execution state
go
Start/continue program execution
halt
Stop program execution
list_breakpoints
List all active breakpoints
read_memory
Read target memory (hex dump format)
read_memory_cached
Read through CPU data cache
read_memory_physical
Read bypassing cache
read_register
Read a single CPU register
read_registers
Read multiple registers at once
read_variable
Read a C/C++ variable by symbol name
reset
Reset the target CPU
run_practice
Run a PRACTICE (.cmm) script with timeout
set_action_breakpoint
Execute a TRACE32 command on hit
set_breakpoint
Set a program/read/write/readwrite breakpoint
set_conditional_breakpoint
Breakpoint with HLL condition (e.g., i > 100)
set_count_breakpoint
Stop after N-th hit (loop debugging)
set_data_breakpoint
Trigger on memory access with optional value match
set_task_breakpoint
Trigger only for a specific OS task/thread
set_temporary_breakpoint
Auto-deletes after first hit
status
Get connection status, TRACE32 version, and system state
step
Single-step execution (into, over, or out)
symbol_by_address
Look up symbol name by address
symbol_by_name
Look up symbol address by name
toggle_breakpoint
Enable/disable a breakpoint without deleting
var_view
View a variable/struct/array with full expansion
write_memory
Write data to target memory
write_register
Write a value to a CPU register
write_variable
Write a value to a C/C++ variable
Tool change history
FAQ
Questions about Debugforge MCP Server
- How do I connect Debugforge MCP Server to Claude?
- Run `claude mcp add debugforge -- uvx debugforge` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
- Is Debugforge MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Debugforge MCP Server do?
- Debugforge MCP Server documents 40 tools to the agent, including clear_all_breakpoints, connect, delete_breakpoint. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.