Kora

Created By
Idkasam4 months ago
Deterministic authorization for AI agent spending — budget checks, spend authorization with Ed25519 cryptographic seals, and audit logs.
Overview

Kora MCP Server gives AI agents (Claude, GPT, etc.) financial controls — every spend must be authorized before money moves. 5 tools:

kora_check_budget — Check remaining daily/monthly spending limits kora_spend — Authorize a spend. Returns APPROVED with Ed25519 cryptographic seal, or DENIED with reason and suggestion kora_recent_activity — View recent authorization history kora_health — Check if Kora is reachable before spending kora_audit — View recent admin actions on the mandate

How it works: Agent calls kora_spend with amount, vendor, currency, and reason. Kora evaluates the mandate (daily limits, vendor allowlist, time windows) and returns a deterministic APPROVED or DENIED. No ML, no probabilistic logic — pure rule evaluation with cryptographic proof. Fail-closed: If Kora is unreachable, the agent gets an explicit "DO NOT PROCEED" message. No silent failures, no unauthorized spending. Install: pip install kora-mcp-server Repo: https://github.com/Idkasam/kora-mcp-server Patent: PCT/EP2025/053553

Server Config

{
  "mcpServers": {
    "kora": {
      "command": "kora-mcp",
      "env": {
        "KORA_API_URL": "https://api.koraprotocol.com",
        "KORA_AGENT_SECRET": "kora_agent_sk_...",
        "KORA_MANDATE": "mandate_...",
        "KORA_ADMIN_KEY": "kora_admin_sk_..."
      }
    }
  }
}
Project Info
Created At
4 months ago
Updated At
4 months ago
Author Name
Idkasam
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Docwand

14 hours ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

14 hours ago