Boyce runs on your own machine — the client starts it, so there is no endpoint to ping. 66 installs a week from pypi. Last commit 28 Apr 2026.
Deterministic SQL compiler for AI agents. Your agent stops guessing SQL.
We read the source, 20 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
result = subprocess.run(cmd, capture_output=True, timeout=60)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add boyce -- uvx boyce
{
"mcpServers": {
"boyce": {
"args": [
"boyce"
],
"command": "uvx"
}
}
}
[mcp_servers.boyce]
command = "uvx"
args = ["boyce"]
{
"mcpServers": {
"boyce": {
"args": [
"boyce"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"boyce": {
"args": [
"boyce"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
BOYCE_DB_URL (PostgreSQL or Redshift connection string. Optional — tools work without live DB; required for live profiling and EXPLAIN pre-flight.), BOYCE_PROVIDER (LLM provider for the NL→StructuredFilter planner (anthropic, openai). MCP hosts using their own model should not set this — the host's model does the reasoning and Boyce receives a pre-built StructuredFilter.), ANTHROPIC_API_KEY (Required only when BOYCE_PROVIDER=anthropic and the host does not supply its own model. MCP hosts (Claude Desktop, Cursor, Claude Code, Codex, Cline, Windsurf, JetBrains) do not need this.).
The author declared them in the registry entry; get the values from the project itself.
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
100 deterministic tools for your AI: logs, tests, SQL, diagrams, SPARQL. Local, no network.
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
Deterministic validation for AI-generated artifacts: JSON Schema, OpenAPI response, SQL syntax.
Deterministic SQL formatting across 19 dialects (postgres, mysql, snowflake, bigquery, etc.).
Persistent memory for AI coding agents: one Rust binary, one local SQLite database.
Local memory for AI agents. One SQLite file on your machine — no cloud, no account.
ClickHouse query & management for AI agents — SQL-classified read/write/destructive gating.
Answers built from our own checks of this server.