Skip to main content
Glama
306,577 tools. Last updated 2026-07-25 15:05

"Reliable sources for use in training language models" matching MCP tools:

Matching MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    Classifies development task complexity (LIGHT/MEDIUM/HEAVY) and recommends the most cost-efficient AI model per provider, enabling optimized model selection for coding tasks.
    Last updated
    3
    26
    MIT
  • A
    license
    -
    quality
    D
    maintenance
    Provides comprehensive access to Strava API for marathon training and race analysis, enabling language models to query athlete data, analyze training patterns, track performance metrics, monitor heart rate zones, and detect injury risks.
    Last updated
    1
    MIT

Matching MCP Connectors

  • ifsc-in MCP — Indian bank branch IFSC code lookup via Razorpay's open

  • India Open Government Data (OGD) Platform MCP — data.gov.in

  • Retrieve all valid news language codes to filter news searches by language. Use these codes as input values for news queries.
    MIT
  • Get the distribution of GPU workload types (inference, training, etc.) for the last N hours to understand GPU fleet utilization.
    MIT
  • List available models with configuration options for workspace pipelines and indexes. Filter by provider, model name, or connection status to identify suitable models.
    Apache 2.0
  • List the available LoRA training flows and base models for character LoRA on FLUX.1-dev, with default parameters. Call this first to understand what train_start expects.
    MIT
  • Stop a running training job and mark it as cancelled. Preserves saved checkpoints in the job's output directory.
    MIT
  • Retrieve SequenceMiner model health and training statistics per chain, including training sequence count and last retrain time, for a fee of $0.01 USDC on Base mainnet.
    MIT
  • Retrieve available voices for AI agents, including IDs, names, gender, language, and supported models. Filter by gender, language, or include cloned voices.
    MIT