Blocks generated by gr-mcp now have a first-class path to GRC's
graphical editor. Previously, .block.yml was only produced as a
side-effect of full OOT export — now clients can generate YAML
standalone to preview, customize, or use without a full OOT module.
- New MCP tool: generate_grc_yaml (registered in block dev mode)
- New model: GrcYamlResult with yaml_content, notes, filename
- Enhanced YAML generation: flags, asserts from min/max bounds,
parameter descriptions, docstring extraction
- New prompt resource: prompts://block-generation/grc-yaml
- 10 new unit tests for GRC YAML generation (475 total, 7 skipped)
Runtime tools now register on-demand rather than at startup:
- get_runtime_mode(): check mode status and available capabilities
- enable_runtime_mode(): dynamically register 36 runtime tools
- disable_runtime_mode(): remove runtime tools when not needed
At startup, only 33 design-time tools are registered. When runtime mode
is enabled, tool count increases to 69. This reduces context usage
significantly when only doing flowgraph design work.
Uses FastMCP's add_tool/remove_tool API for dynamic registration,
following MCP spec's notifications/tools/list_changed pattern.
build_module() now re-registers when a Docker image exists but the
registry entry is missing (e.g., after manual registry edits or
schema migrations). This fixes auto-build in combo workflows where
a module's image exists but isn't tracked.
Also fixes gr-rds catalog branch (main → maint-3.10) and adds
tests for per-entry registry validation and orphan re-registration.
Combine multiple OOT modules into a single Docker image using
multi-stage COPY from existing single-OOT images. No recompilation
needed — fast and deterministic.
New MCP tools: build_multi_oot_image, list_combo_images, remove_combo_image
Also hardens _load_registry() to validate per-entry instead of
all-or-nothing, preventing one corrupt entry from discarding the
entire registry.
- Fix branch names for 5 modules discovered during install attempts:
ieee802_11, ieee802_15_4, adsb (maint-3.10), iridium, nrsc5 (master)
- Remove packet_radio (repo gone/private)
- Add build_deps for modules that need them (castxml, autotools, Qt5)
- Add fix_binding_hashes.py helper script to Dockerfile builds to
prevent castxml regen failures from stale pybind11 header hashes
- Use tar build context in Docker builds to support COPY instruction
- Note inspector as incompatible with GR 3.10 (API changes)
Successfully built: ieee802_11, ieee802_15_4, adsb, iridium, nrsc5
Curated catalog of 20 GNU Radio OOT modules served via two MCP
resources (oot://directory, oot://directory/{name}). Each entry
includes git URL, branch, build deps, and a ready-to-use
install_oot_module() example.
Modules are tagged preinstalled when they ship with the
gnuradio-runtime base Docker image (12 of 20), so agents can
distinguish what's already available from what needs building.
Single MCP tool call builds any GNU Radio OOT module from a git repo
into a reusable Docker image. Generates a Dockerfile from template,
builds via Docker SDK, and tracks results in a persistent JSON registry.
New tools: install_oot_module, list_oot_images, remove_oot_image
Also changes launch_flowgraph default xmlrpc_port from 8080 to 0 (auto)
Flowgraphs generated by GRC on the host often fail in Docker containers
due to three issues:
1. message_debug constructor signature changed between GR 3.10.5 and
3.10.12 — strip the second arg for older runtimes
2. XML-RPC binds to localhost, unreachable from Docker host — rewrite
to 0.0.0.0
3. input('Press Enter to quit:') gets immediate EOF in detached
containers, killing the flowgraph instantly — inject signal.pause()
fallback after EOFError
All patches are applied in a single pass via patch_flowgraph() before
the container launches. The original file is never modified.
Add add_block_path() and get_block_paths() MCP tools for incremental
OOT module loading with BlockPathsModel responses. On startup, auto-scan
/usr/local/share and ~/.local/share for OOT blocks so modules like
gr-lora_sdr are available without manual configuration.
Add comprehensive integration tests that don't require Docker:
- test_xmlrpc_subprocess.py: Tests XmlRpcMiddleware against a real
subprocess-based XML-RPC server. Covers connection, variable
discovery, get/set operations, and flowgraph control (18 tests).
- test_mcp_runtime.py: Tests MCP runtime tools via FastMCP Client.
Verifies connect, disconnect, list_variables, get_variable,
set_variable, and flowgraph control work end-to-end (15 tests).
- test_fm_scanner.py: Tests signal probe functionality and FM scanner
parsing. Includes unit tests for helper functions and integration
tests for flowgraph construction with signal probe blocks (18 tests).
All 59 integration tests pass. These tests provide faster feedback
than Docker-based tests while still exercising real XML-RPC
communication and flowgraph construction.
The lru_cache on get_block() caused three cache coherence bugs:
1. Removed blocks remained accessible — set_block_params would
modify a detached block object that no longer exists in the
flowgraph, so save_flowgraph would serialize stale state.
2. Re-created blocks with the same auto-generated name would
return the cached (removed) block instead of the new one.
3. Renamed blocks (via set_block_params id=...) left phantom
cache entries under the old name.
Fix: always look up blocks from the live flowgraph. Block lookup
is a linear scan of typically <20 blocks — no cache needed.
Raises KeyError instead of StopIteration for missing blocks.
GRC's SimpleXMLRPCServer uses register_instance() which doesn't
expose system.listMethods. Wrap the connectivity check in a
try/except so a Fault is treated as "connected" while
ConnectionRefusedError still propagates.
Prevent silent Docker bind failures by checking port availability
before container creation. Supports auto-allocation (port=0) and
patches compiled flowgraphs when the embedded XML-RPC port differs
from the requested port.
- Bump version to 0.2.0
- Require Python 3.14+
- Update to FastMCP 3.0.0b1 with new Client API
- Update tests for FastMCP 3.0 (Pydantic models in .data)
- Pin modern dependency versions
