Boyce

Created By
boyce-io2 months ago
Give AI agents structured database intelligence. Deterministic SQL, NULL trap detection, EXPLAIN pre-flight. MIT licensed.
Overview

Boyce is an MCP server that gives AI agents structured database intelligence to generate correct, safe SQL — deterministically.

The problem: AI agents querying databases without context produce unreliable SQL. They guess join paths, miss NULL distributions, and silently return wrong results. An unguarded equality filter on a column with 30% NULLs silently drops those rows — and the agent never knows.

What Boyce does:

  • SQL Compiler — NL → StructuredFilter → deterministic SQL. Same inputs, same SQL, byte-for-byte, every time. Zero LLM in the SQL compiler.
  • Database Inspector — Live Postgres/Redshift adapter. Real schema, real NULL distributions before writing a single filter.
  • Query Verification — EXPLAIN pre-flight on every query. Bad SQL caught at planning time, not at 2am.

For MCP hosts (Claude Desktop, Cursor, Claude Code, etc.): No API key needed. The host LLM reads the schema via get_schema, constructs a query, and Boyce compiles deterministic SQL.

8 MCP tools: ingest_source, ingest_definition, get_schema, ask_boyce, validate_sql, query_database, profile_data, check_health.

10 source parsers: dbt manifest, dbt project, LookML, raw DDL, SQLite, Django, SQLAlchemy, Prisma, CSV, Parquet.

Dialects: Redshift, Postgres, DuckDB, BigQuery.

Named for Raymond F. Boyce, co-inventor of SQL (1974). MIT licensed.

Server Config

{
  "mcpServers": {
    "boyce": {
      "command": "uvx",
      "args": [
        "boyce"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
boyce-io
Star
-
Language
-
License
-
Category
Tags

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