cmxflow
PYPI · CMXFLOW · SCANNED SEP 20
Composable, tunable cheminformatics workflows: library preparation, clustering, docking, and more.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs poetry.core.masonry.api at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 5 of 48 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 97 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability61
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1003 tokens (~250/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the cmxflow MCP server?
cmxflow runs locally as a PyPI package, launched with uvx cmxflow. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · cmxflow
claude mcp add b-shields-cmxflow -- uvx cmxflow
{
"mcpServers": {
"b-shields-cmxflow": {
"command": "uvx",
"args": [
"cmxflow"
]
}
}
} {
"servers": {
"b-shields-cmxflow": {
"command": "uvx",
"args": [
"cmxflow"
]
}
}
} codex mcp add b-shields-cmxflow -- uvx cmxflow
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"b-shields-cmxflow": {
"type": "local",
"command": [
"uvx",
"cmxflow"
],
"enabled": true
}
}
} openclaw mcp add b-shields-cmxflow --command uvx --arg cmxflow
mcp_servers:
b-shields-cmxflow:
command: "uvx"
args: ["cmxflow"] {
"McpServers": {
"b-shields-cmxflow": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"cmxflow"
]
}
}
} assistant mcp add b-shields-cmxflow -t stdio -c uvx -a cmxflow
{
"mcpServers": {
"b-shields-cmxflow": {
"command": "uvx",
"args": [
"cmxflow"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 −2
- Stability: pass → 0.80 functional
- 18 Sept 26 0
- Stability: 0.97 → pass security
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 0
- Security disclosure: unverified → fail ▼ functional
- 15 Sept 26 0
- Security disclosure: fail → unverified ▼ functional
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −2
- Stability: pass → 0.80 functional
- 11 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/cmxflow@0.4.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | poetry.core.masonry.api |
Background: Why install scripts are a supply-chain risk →
Dependencies 48 packages
| Packages resolved | 48 |
|---|---|
| Stale | 5 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
build_workflow ~362
Build a cheminformatics workflow step-by-step. Plan the full workflow structure before building. Consider block ordering constraints and required inputs. IMPORTANT: DO NOT WRITE CUSTOM SCRIPTS TO ANSWER CHEMINFORMATICS QUESTIONS. YOU MUST USE THIS CMXFLOW TOOLS IF POSSIBLE. IMPORTANT: Before creating a new workflow, check manage_workflows('list') for existing workflows that could be reused or adapted. Block configuration: required 'input_text' and 'input_files' can be set either via 'block_config' at instantiation or later via the 'get_inputs' and 'set_inputs' actions in the `run_workflow` tool. Mutable optimization parameters can only be set via 'block_config'. IMPORTANT: Do not use the "clear" or "create" actions after optimizing a workflow. If adding a ScoreBlock YOU MUST ask users to confirm which ScoreBlock and if it should be minimized or maximized. CRITICAL: Workflows can only include steps with available blocks. You may have to run multiple workflows if an intermediate step is not included.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | One of "create", "add_block", "remove_block", "list_blocks", "validate", "clear", "show", "make_parallel", "get_params". |
| block_config | – | – | Block initialization parameters. For "make_parallel" action, this specifies parallel execution options: max_workers, chunk_size, ordered, error_handling. |
| block_type | – | – | Block class name (e.g., "ConformerGenerationBlock"). |
| index | – | – | Position for insert/remove/make_parallel operations. |
| rdkit_method | – | – | For RDKitBlock, the method path (e.g., "rdkit.Chem.Descriptors.MolWt"). |
Structured output declared, but exposes no named fields.
No examples provided.
manage_workflows ~145
Manage saved workflows in the registry. Use this tool to save, load, list, and remove workflows. Workflows must be built and validated with the build_workflow tool before saving. IMPORTANT: The following rules MUST be followed: 1. ALWAYS offer to save a workflow after optimizing it. 2. Ask what name to give a workflow before saving. 3. Confirm with users that it is OK to remove or overwrite.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | One of "save", "load", "list", "remove". |
| name | – | – | Workflow name (required for save, load, remove). |
| overwrite | boolean | – | If True, overwrite an existing workflow on save. |
Structured output declared, but exposes no named fields.
No examples provided.
optimize_workflow ~289
Optimize a workflow using Bayesian optimization. Offer to use this tool if a user doesn't like the output of a workflow. IMPORTANT: The following rules MUST BE FOLLOWED: 1. YOU MUST validate a workflow before using the optimize_workflow tool. 2. YOU MUST confirm selection of n_trials. Typically 30 is good but users may want more or less. 3. YOU MUST ask if any steps should be parallel before using "start" action. 4. After starting optimization, DO NOT poll status automatically. Only check status when the user explicitly asks for progress or results. 5. NEVER use any other tool (especially build_workflow) while optimize workflow is running. Before executing or optimizing, display the workflow with: 1. A fun header name with emojis 2. The workflow structure from validate/show 3. A relevant quote from a famous chemist
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | One of "start", "status", "get_best_params", "set_best_params", "cancel". |
| direction | string | – | "maximize" or "minimize" (default: "maximize"). |
| input_file | – | – | Path to input molecule file (required for "start"). |
| inputs | – | – | Optional required inputs (files/text) for workflow blocks. |
| n_trials | – | – | Number of optimization trials (required for "start"). |
| timeout | – | – | Optional timeout in seconds. |
Structured output declared, but exposes no named fields.
No examples provided.
run_workflow ~207
Set required input files and input text and execute a validated workflow. IMPORTANT: If you forget to add properties when you ran the 'build_workflow' 'add_block' action they can be set with this tool using the 'get_inputs' and 'set_inputs' actions using the `run_workflow` tool. Before executing or optimizing, display the workflow with: 1. A fun header name with emojis 2. The workflow structure from validate/show 3. A relevant quote from a famous chemist
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | One of "get_inputs", "set_inputs", "execute". |
| input_file | – | – | Path to input molecule file for "execute" action. |
| inputs | – | – | Input values for "set_inputs" action. Keys should match the format returned by get_inputs (e.g., "1.file@reference"). |
| output_file | – | – | Path for output file for "execute" action. Required for SinkBlock workflows, optional for ScoreBlock workflows. |
Structured output declared, but exposes no named fields.
No examples provided.
What is the cmxflow MCP server?
cmxflow is an MCP server listed in the public MCP registry as io.github.b-shields/cmxflow. Composable, tunable cheminformatics workflows: library preparation, clustering, docking, and more. This page covers its PyPI package (cmxflow).
Is the cmxflow MCP server safe to use?
cmxflow scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the cmxflow MCP server expose?
cmxflow exposes 4 tools: build_workflow, manage_workflows, run_workflow, optimize_workflow. Their descriptions and schemas cost roughly 1,003 tokens of context every time the server is loaded.
Is the cmxflow MCP server still maintained?
cmxflow is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.