PluginBench
MCP Server

io.github.liveplex-cpu/fiber MCP Server

io.github.liveplex-cpu/fiber

RepositoryRegistry
How to choose

What this kind of tool is for

  • Automate a build, test, or deployment step you repeat by hand.
  • Review or refactor code in an existing repository without leaving your agent.
  • Bridge an internal service or CLI into the agent toolset.

How to compare servers like this

Scope of control:
Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
Environment fit:
Match the runtime it expects (Node, Python, a container) to what you actually run.
Maintenance signal:
Check the last-commit date — dev tooling that lags upstream breaks first.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.liveplex-cpu/fiber MCP server?

Optical ops MCP for AI DCs — gNMI, ML RUL, Digital Twin, NCCL, SPARQL semantic

How to install io.github.liveplex-cpu/fiber

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • FIBER_API_URL

    Base URL of the FIBER deployment (e.g., https://api.fiber.ac or http://localhost:8000 for self-hosted).

  • FIBER_API_KEY
    required
    secret

    Bearer token for the FIBER API. Role determines which tools work: viewer (24 read tools), operator (+write), admin (all).

  • FIBER_ENABLE_WRITE

    Set to 1 to expose write tools: demo trigger, NCCL ingest, RMA create. Defaults to read-only for safety.

  • FIBER_MCP_TOOLS_ALLOWLIST

    (v1.0.2) Optional CSV of tool names. When set, only these tools are exposed — letting operators scope autonomous agents to a minimum surface (e.g. 'fiber_health,fiber_cluster_overview,fiber_list_alerts'). Empty = all tools exposed (default).

  • FIBER_HTTP_TIMEOUT

    Per-request HTTP timeout in seconds. Increase if running Digital Twin Monte Carlo with iterations>1000.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "fiber": {
      "command": "python",
      "args": [
        "fiber-mcp"
      ],
      "env": {
        "FIBER_API_URL": "<YOUR_FIBER_API_URL>",
        "FIBER_API_KEY": "<YOUR_FIBER_API_KEY>",
        "FIBER_ENABLE_WRITE": "<YOUR_FIBER_ENABLE_WRITE>",
        "FIBER_MCP_TOOLS_ALLOWLIST": "<YOUR_FIBER_MCP_TOOLS_ALLOWLIST>",
        "FIBER_HTTP_TIMEOUT": "<YOUR_FIBER_HTTP_TIMEOUT>"
      }
    }
  }
}

Related MCP servers

Build, inspect and read adaptive A/B tests. Config travels in the URL; no account or API key needed.

View repository →
SKskillmem logo

skillmem

Active

Skill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.

6
Python
Apache-2.0
View repository →

Admin an Alby Hub Lightning node from an agent: info, balances, channels; safety-gated writes.

0
TypeScript
MIT
View repository →

Search and install 20,000+ security-graded MCP servers and agent skills.

1
JavaScript
MIT
View repository →

Live tennis scores, players, rankings, odds and win-probability for ATP, WTA, Challenger, ITF and juniors.

191
TypeScript
MIT
View repository →

Build and update a visual operating cockpit for AI-native solo founders.

1
Python
MIT
View repository →