MCP

Created By
wandba year ago
A collection of MCP (Model Context Protocol) tools and examples for wandb and weave
Overview

what is MCP?

MCP (Model Context Protocol) is a collection of tools and examples designed to enhance the functionality of wandb and weave, facilitating better model management and context handling.

how to use MCP?

To use MCP, clone the repository from GitHub, and explore the provided tools and examples to integrate with your wandb and weave projects.

key features of MCP?

  • A comprehensive set of tools for managing model contexts.
  • Examples demonstrating the integration with wandb and weave.
  • Support for various model management tasks.

use cases of MCP?

  1. Streamlining model training workflows with context management.
  2. Enhancing data visualization in wandb projects.
  3. Facilitating collaboration on model development using shared contexts.

FAQ from MCP?

  • What is the purpose of MCP?

MCP aims to provide tools that simplify the management of model contexts in machine learning projects.

  • Is MCP compatible with all versions of wandb?

Yes! MCP is designed to work with the latest versions of wandb and weave.

  • How can I contribute to MCP?

Contributions are welcome! Please check the GitHub repository for guidelines.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
wandb
Star
0
Language
-
License
Apache-2.0 license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago