neuralcontrol-mcp
MCP Server for the AI Control Plane — gives AI editors (Cursor, Claude, Windsurf) live access to your endpoint configs, real-time metrics, Request Coalescing examples, and SDK documentation.
Installation
pip install neuralcontrol-mcp
Configuration
Add this to your AI editor's MCP config (e.g. ~/.cursor/mcp.json or claude_desktop_config.json):
{
"mcpServers": {
"neuralcontrol": {
"command": "neuralcontrol-mcp",
"env": {
"CONTROL_PLANE_URL": "https://api.neuralcontrol.online",
"NEURALCONTROL_API_KEY": "acp_your_key_here"
}
}
}
}
Or copy .env.example to .env and fill in your values, then run directly:
neuralcontrol-mcp
# or
python -m server
What you get
Once connected, your AI editor can:
| Tool | What it does |
|---|---|
get_endpoint_config |
Live AI flags (caching, circuit breaker, rate limits) for any endpoint |
get_recent_metrics |
Real-time p50/p95/p99 latency + error rates |
get_adaptive_timeout_status |
Which endpoints are currently timing out |
get_ai_thresholds |
Raw AI-calculated threshold values |
get_all_ai_insights |
Why the AI enabled/disabled each feature |
get_open_incidents |
Active latency spikes or error surges |
get_active_overrides |
Manual overrides currently in effect |
create_threshold_override |
Immediately override a threshold (e.g. during an incident) |
get_sdk_setup_instructions |
Get integration code for your service |
get_feature_documentation |
Full docs for any protection feature |
get_feature_flags |
Fetch all feature flags for a service |
set_feature_flag |
Create/update a feature flag's rollout |
get_trace |
Fetch full distributed trace waterfall |
Environment Variables
| Variable | Description | Default |
|---|---|---|
CONTROL_PLANE_URL |
URL of your running control-plane backend | http://localhost:8000 |
NEURALCONTROL_API_KEY |
Your NeuralControl API key | (required) |
Hosted / Docker
To run as a persistent HTTP/SSE server (for team-wide access):
docker build -t neuralcontrol-mcp .
docker run -p 8080:8080 \
-e CONTROL_PLANE_URL=https://your-api.yourdomain.com \
-e NEURALCONTROL_API_KEY=acp_xxx \
neuralcontrol-mcp
Then connect via URL:
{ "mcpServers": { "neuralcontrol": { "url": "http://localhost:8080/sse" } } }
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for neuralcontrol-mcp 1.3.0
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 |
|---|---|---|---|---|
| neuralcontrol_mcp-1.3.0.tar.gz | 10.5 kB | With provenance | Details for neuralcontrol_mcp-1.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| neuralcontrol_mcp-1.3.0-py3-none-any.whl | Python 3 | none | any | Details for neuralcontrol_mcp-1.3.0-py3-none-any.whl |
Total release size: 20.9 kB
Release files / neuralcontrol_mcp-1.3.0.tar.gz
| Download URL | neuralcontrol_mcp-1.3.0.tar.gz |
|---|---|
| Size | 10.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1e72aad002981022bda31ab65a16e2d93e043dbf197d066ab00bed1a66ebb9de
|
|
BLAKE2b-256 checksum How to use checksums |
366614b63f6a611e78b16ac767f638853523dbf18ff44c005fdd7a76ab13f085
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 27, 2026.
Transparency logRelease files / neuralcontrol_mcp-1.3.0-py3-none-any.whl
| Download URL | neuralcontrol_mcp-1.3.0-py3-none-any.whl |
|---|---|
| Size | 10.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ba17f88c42be1001c4b694e461ead59b03c5bf8a477dce71149e363c7b486d57
|
|
BLAKE2b-256 checksum How to use checksums |
aaa82c9e03267a9edbcf8a2d9120a819a50bf5d6280c4d6e22c56607bc472f43
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 27, 2026.
Transparency logSecurity for neuralcontrol-mcp 1.3.0
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for neuralcontrol_mcp-1.3.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 27, 2026.
Transparency logA 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.
