inferexai-mcp
Official MCP (Model Context Protocol) server for InferexAI — lets Claude Desktop, Claude Code, or any MCP-compatible AI agent manage your LLM gateway account conversationally.
Installation
pip install inferexai-mcp
Quick start
INFEREXAI_API_KEY=sk-live-your-key-here inferexai-mcp
Claude Desktop setup
Add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"inferexai": {
"command": "inferexai-mcp",
"env": {
"INFEREXAI_API_KEY": "sk-live-your-key-here"
}
}
}
}
Restart Claude Desktop. You can now ask Claude things like:
"What's my InferexAI wallet balance?" "Create a new API key called 'staging' that expires in 3 months" "Show me my usage for the last 7 days" "Invite dev@acme.com to my organisation"
Claude Code setup
claude mcp add inferexai -e INFEREXAI_API_KEY=sk-live-your-key-here -- inferexai-mcp
Available tools
| Tool | Description |
|---|---|
wallet_balance |
Get current wallet balance in INR |
list_keys |
List all API keys with status, scopes, limits |
create_key |
Create a new API key (name, expiry, scopes) |
revoke_key |
Permanently revoke a key by ID |
query_usage |
List recent usage events with filters |
usage_summary |
Aggregated token, cost, error stats |
get_account |
Account details and KYC status |
set_low_balance_alert |
Set wallet alert threshold in ₹ |
get_org |
Organisation info and wallet |
create_org |
Create a new organisation |
list_org_members |
List org members with roles |
invite_org_member |
Invite a member by email |
remove_org_member |
Remove a member by user ID |
Environment variables
| Variable | Required | Default |
|---|---|---|
INFEREXAI_API_KEY |
Yes | — |
INFEREXAI_BASE_URL |
No | https://inferexapi.cloudvoice.in |
Requirements
- Python 3.10+
mcp >= 1.0.0httpx >= 0.24.0
Links
License
Metadata
Release files for inferexai-mcp 0.1.0
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 |
|---|---|---|---|---|
| inferexai_mcp-0.1.0.tar.gz | 4.8 kB | Without provenance | Details for inferexai_mcp-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| inferexai_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for inferexai_mcp-0.1.0-py3-none-any.whl |
Total release size: 10.4 kB
Release files / inferexai_mcp-0.1.0.tar.gz
| Download URL | inferexai_mcp-0.1.0.tar.gz |
|---|---|
| Size | 4.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
338b8c062f6ee1737f1b8005f19553c9b55317e5d59e6a0d0a2bbe600289b657
|
|
BLAKE2b-256 checksum How to use checksums |
46b3b90d433af836f998a8275fc2f8ed61aa211ecbfb9d30a2e0f88952f58c53
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.8
|
Release files / inferexai_mcp-0.1.0-py3-none-any.whl
| Download URL | inferexai_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ab2c4c3afd3d5ba53a0d779f5ed5adb6c14172bef4607416dbf345b3584f884f
|
|
BLAKE2b-256 checksum How to use checksums |
b96f50d124b548549f82b471eed49978238025d81a7dbcdfc95cee9d4ee69121
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.8
|
Security for inferexai-mcp 0.1.0
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.
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.