Ellisys MCP server
An MCP (Model Context Protocol) server that lets AI agents and chat hosts (e.g. Claude Desktop) drive a running Ellisys protocol analyzer through the Remote Control automation API.
Four tools: analysis_guide (the SDK agent guide + recipes), analysis_status (connectivity +
analyzer state + markers), analysis_explore (overview/protocol-layer survey, vocabulary,
devices, anchors), analysis_run_python (persistent Python session with the SDK preloaded --
all actions and analysis happen here). The session includes install("pkg", ...) for
on-demand libraries, show(figure) to return matplotlib figures as images, and attach(path)
to return small files (<= 4 MB) with the result. Use uvx "ellisys-analysis-mcp[analysis]@latest" to
have matplotlib and pandas preinstalled.
Use
Prerequisite: uv (it provisions Python and the packages; no
Python installation needed). Install once -- Windows: winget install astral-sh.uv; macOS:
brew install uv; Linux: curl -LsSf https://astral.sh/uv/install.sh | sh -- then verify
uvx --version in a new terminal and (re)start your MCP host.
Host configuration:
{ "command": "uvx", "args": ["ellisys-analysis-mcp@latest"] }
The @latest suffix makes uvx pick up new releases on every server start (updating is just a
host restart); without it, uvx reuses the first resolved version until uv cache clean
ellisys-analysis-mcp. Pin a fixed version with ellisys-analysis-mcp@0.1.3.
The analyzer host/port default to localhost:12345; override with --host/--port arguments
or the ELLISYS_HOST/ELLISYS_PORT environment variables. The analyzer application must be
running with the Remote Control plugin enabled (see the Remote Control User Guide). File paths
in load/save/export operations are resolved on the analyzer machine.
Documentation
The full SDK guide and the per-product Remote Control User Guides ship in the release archives:
remote_api_analyzer.zip /
bta_remote_api.zip. For agents, the
analysis_guide tool returns the authoritative usage guide directly.
License
GPL-2.0-only (like the Remote Control plugin and SDKs, which link ZeroC Ice).
Metadata
Release files for ellisys-analysis-mcp 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ellisys_analysis_mcp-0.1.3.tar.gz | 11.3 kB | Without provenance | Details for ellisys_analysis_mcp-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ellisys_analysis_mcp-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for ellisys_analysis_mcp-0.1.3-py3-none-any.whl |
Total release size: 21.7 kB
Release files / ellisys_analysis_mcp-0.1.3.tar.gz
| Download URL | ellisys_analysis_mcp-0.1.3.tar.gz |
|---|---|
| Size | 11.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
61b13278e003ebbcf7bb047d4058fc2804f0c423f7fd3cee6f422721bdfd5708
|
|
BLAKE2b-256 checksum How to use checksums |
6221a38edd8b7bd265061a85c26950a773ea5812c6176c697f372b564e3d0e02
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.2
|
Release files / ellisys_analysis_mcp-0.1.3-py3-none-any.whl
| Download URL | ellisys_analysis_mcp-0.1.3-py3-none-any.whl |
|---|---|
| Size | 10.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8229cf61f45e61654c0f578a495d56302ee0d93d39286a2344c78ea875c65c90
|
|
BLAKE2b-256 checksum How to use checksums |
5a4f1881bf7607a7d9234ac0bbd8ec0ae92a00371f10ab01dd9f6705831f4046
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.2
|
Security for ellisys-analysis-mcp 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
