
Sakila MCP
io.github.pantoniadesPublished by GitHub account pantoniadesv0.1.2Updated Nov 19, 2026
Read-only MySQL MCP server with a fail-closed SQL classifier and structured results.
Overview
Read-only MySQL MCP server that lets an assistant inspect schemas, run single SELECT queries and read query plans, with a fail-closed SQL classifier.
- What you can do
- Inspect the server: MySQL version and release line, uptime, time zone and key globals
- List databases and tables, with system schemas flagged and engine, row and size estimates
- Describe a table's columns, indexes, foreign keys, engine and collation
- Run one read-only statement with bound parameters, returning structured columns and rows
- Explain a query as JSON or tree with a summary of scans, filesort and temporary tables
- Read a capabilities resource describing version and EXPLAIN format support
- When to use it
- Useful when an assistant needs to explore an unfamiliar MySQL schema, answer questions about how tables relate, or diagnose why a query is slow, without giving it write access.
- Requirements
- Local process run with uvx; Python 3.12 or later and uv. A MySQL 8.4 or later account (8.0 best-effort) with read-only grants. Configure via SAKILA_MCP_HOST, SAKILA_MCP_PORT, SAKILA_MCP_USER (required), SAKILA_MCP_PASSWORD, SAKILA_MCP_DATABASE_ALLOWLIST, or a TOML file passed with --config. Network access to the database.
Installation
In SourceWeft
- Open Sakila MCP in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
sakila-mcp
sakila-mcp is an MCP server that lets an LLM agent inspect and query any MySQL database, read-only, with a fail-closed SQL classifier between the agent and the server.
sakila-mcp is a general-purpose MySQL MCP server for any MySQL database. It is named after Sakila, the MySQL dolphin mascot, and is not specific to the Sakila sample database.
Independent open-source project. Not affiliated with, sponsored by or endorsed by Oracle. MySQL is a trademark of Oracle and/or its affiliates.
Status: v0.1 (0.1.1 is the first release on PyPI). What's described here works today. Expect the interface to change.
Quickstart
You need uv and a MySQL account that can only read (the grants are under Safety model).
Then ask "what's in app_db and how do orders relate to customers?" or "why is this query slow?". Any MCP client that speaks stdio works; see Use it.
What makes it different
- It fails closed. A statement the classifier can't parse is refused, and so is any function that isn't a known MySQL built-in.
- It doesn't trust one lexer. Comments are re-scanned with MySQL's own rules, because a parser and the server can disagree about where a comment ends.
- A refusal is a result, not an error: a code, a reason and a suggestion, so the agent can rephrase instead of giving up.
- Everything is bounded without touching your SQL: rows, cell size and execution time
are capped, and no
LIMITis ever added to a query. - The classifier isn't the only layer. Sessions are read-only transactions, re-initialised on every checkout, and the connection can't send more than one statement.
- It knows MySQL's release lines (LTS, Innovation, calendar versions) and reads both
EXPLAIN FORMAT=JSONshapes. - It says where it stops: the database allowlist is a name filter, and the real boundary is the account's grants.
What it does
Six tools, all read-only:
Plus one resource, mysql://capabilities: version, release line, EXPLAIN JSON format
version, and whether sys is visible.
Results are structured, not prose. DECIMAL comes back as a string so it stays exact,
dates and times as ISO 8601, JSON parsed, binary as <binary N bytes>. Long cells are
cut at max_cell_bytes with a marker saying how big they were.
When the server says no, the agent gets a result with refused: true, a reason and a
suggestion, not an error, so it can rephrase. That includes SQL the classifier can't
parse. Mistakes MySQL reports (unknown table or column, wrong parameter count) and
infrastructure failures are tool errors.
Safety model
Every session, on every pool checkout:
SET SESSION TRANSACTION READ ONLYmax_execution_time=statement_timeout_ms,lock_wait_timeout= 5 s- connection attributes
program_name=sakila-mcpandsakila_mcp_version, and every statement is tagged/* sakila-mcp tool=... */, so you can find it in the processlist and performance_schema
Every statement from run_query and explain_query goes through a SQL classifier
(sqlglot plus token-level checks) before it reaches MySQL. It fails closed: if it can't
parse it, it refuses it.
- Allowed: one SELECT, WITH, TABLE, VALUES, DESCRIBE, EXPLAIN, or a SHOW from a fixed list.
- Refused: everything else, more than one statement,
/*! ... */version comments,INTO(OUTFILE, DUMPFILE, variables), locking reads (FOR UPDATE,FOR SHARE),:=assignment, theSET_VARhint,EXPLAIN ANALYZE(it executes), functions that block, lock, wait or read files (SLEEP,BENCHMARK,GET_LOCK,LOAD_FILE, ...), and any function that isn't a known built-in (stored functions can write). - Parameters are bound by the server (
PREPARE/EXECUTE ... USING), never spliced into the SQL. - Results stop at
max_rows; the query is cut off, not rewritten with aLIMIT.
The database allowlist is a filter on names, not an isolation boundary.
information_schema, performance_schema and sys are always readable, and
SHOW PROCESSLIST, SHOW ENGINE INNODB STATUS and performance_schema statement history
show other sessions' SQL, literal values included. The mysql schema is denied unless
you list it.
The real boundary is the account's grants. Give sakila-mcp its own account with only what it needs:
The password never appears in tool results, logs or error text. There's a test for that.
Requirements
- Python 3.12 or later and uv
- MySQL 8.4 or later. CI runs the integration tests against 8.4, 9.7 and 26.10. 8.0 is tested best-effort: failures there don't block a release, and functions that exist only in 8.0 are refused as unknown.
Install
Nothing to install: uvx sakila-mcp downloads and runs the latest release. Pin a version
with uvx [email protected], or install it with uv tool install sakila-mcp.
To run from a checkout instead, see Development.
Configure
Environment variables (SAKILA_MCP_*), a TOML file passed with --config, or both.
Environment variables win over the file. Keep the password in the file, chmod 600 it,
and keep it out of version control.
The server connects to MySQL on the first tool call, not at startup. It starts and lists its tools even when MySQL is down; a wrong host or password shows up as a tool error on the first call (and in stderr), and the next call tries again.
Use it
Claude Code:
Claude Desktop (claude_desktop_config.json):
Ollama, with local models. Ollama runs the model but isn't an MCP client itself, so use
ollmcp (mcp-client-for-ollama), a
terminal client that connects Ollama models to MCP servers:
It reads the same mcpServers format as Claude Desktop. Save this as, say,
~/.config/sakila-mcp.ollmcp.json:
and start it with a model that supports tool calling. ollama show <model> lists tools
under Capabilities, and https://ollama.com/search?c=tools lists the models that have it:
/tools inside ollmcp turns individual tools on and off. Model choice matters more here
than with a hosted model: a model that is too small may call the wrong tool, invent
arguments, or stop after one call. If that happens, try a larger one. That's a model
problem, not a safety one. The server enforces the same rules whatever is calling it.
Then ask it things like "what's in app_db and how do orders relate to customers?" or "why is this query slow?".
Not in v0.1
Write mode, more than one server per process, HTTP transport, replication / InnoDB /
lock diagnostics, Enterprise Edition features, EXPLAIN ANALYZE, stored functions.
Development
Integration tests need a MySQL server prepared once with tests/integration/setup.sh.
Give it the address the server sees the tests connect from and a letters-and-digits
password (extra arguments go to the mysql client), then point the tests at the server:
.env.test is gitignored. Without it the integration tests skip.
One test is opt-in: it drives Claude Code (claude -p) through every tool against the
test server and checks that the client accepts each result. It needs the claude CLI,
uses your account, and never runs in CI:
Source: README.md at commit a0439a4
Tools
0Version history
1- v0.1.2LatestNov 19, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts