Vivado Agent MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VIVADO_PATH | No | Path to the Vivado executable (e.g., C:\Xilinx\Vivado\2024.2\bin\vivado.bat). If not set, the server searches common Xilinx installation directories and system PATH. |
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 |
|---|---|
| start_vivadoA | Start one headless Vivado Tcl session and optionally open an existing .xpr project. |
| stop_vivadoA | Stop the Vivado process owned by this MCP server. |
| run_tclC | Use raw Tcl as an escape hatch, then refresh project context before further actions. |
| inspect_projectA | Read current project, sources, part, top module, and build-run states. |
| inspect_runB | Inspect an asynchronous job by MCP job ID or a native Vivado run name. |
| run_synthesisB | Launch synthesis idempotently and return a job ID instead of blocking. |
| run_implementationB | Launch implementation only after project and synthesis prerequisites pass. |
| generate_bitstreamA | Launch bitstream generation only when timing and diagnostic gates pass. |
| diagnose_runC | Extract bounded errors and critical warnings from a Vivado run log. |
| check_build_readinessB | Gate bitstream generation on routed state, timing slack, and blocking diagnostics. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| vivado_build_workflow | Guide an Agent through an evidence-driven Vivado build. |
| vivado_debug_workflow | Guide an Agent through bounded, evidence-first run diagnosis. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| current_project_resource | Current project context for read-only Agent grounding. |
TDQS
Scored across 10 tools
Each tool targets a distinct stage or concern: session lifecycle, raw Tcl escape hatch, project/run inspection, build steps, log diagnostics, and readiness gating. No two tools have overlapping purposes, and run_tcl is clearly an escape hatch rather than a duplicate.
All tool names follow a consistent verb_noun pattern in snake_case (start_vivado, inspect_project, run_synthesis, generate_bitstream, check_build_readiness). The naming convention is uniform and predictable, making tool selection straightforward.
With 10 tools, the server is well-scoped for a Vivado build automation agent, covering lifecycle, inspection, build steps, diagnostics, and gating without redundancy. Each tool has a clear responsibility and earns its place.
The tool surface covers the full FPGA build flow: session management, project/run inspection, synthesis, implementation, bitstream generation, and diagnostics/gating. The raw Tcl escape hatch also covers edge cases, so there are no obvious dead ends for the stated purpose.