GoSQLX MCP server
io.github.ajitpratap0/gosqlxajitpratap0streamable-httpv1.17.0Scanned
SQL validation, formatting, parsing, metadata extraction, linting, and security analysis.
7 tools: 7 change things.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- 7 findings
Tools listed without sign-in. Remote posture
With Anlyon
7 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the GoSQLX MCP server can do
The GoSQLX MCP server is published by the GitHub account ajitpratap0. It has 7 tools. It can create or change data (7 tools: analyze_sql, extract_metadata, format_sql, lint_sql and 3 more), but cannot delete data. None of its tools only reads.
1 tool reads private data (analyze_sql); 1 tool brings in text other people can write (analyze_sql).
The fixed checks matched 7 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 13, 2026, version 1.17.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Changes things 7Claude Code: ask
analyze_sqlUse this when the user wants a complete review of a SQL query.Reads private dataReads text others write1 finding
Why it is in this group
- The name "analyze_sql" says "analyze": a word for reading.
- The input takes a statement or command to run (input.sql), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- private-dataThe name "analyze_sql" says "analyze" and "sql": it reads databases.
- private-dataThe description's first sentence says "sql": it reads databases.
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Findings
- Warn
The server marks "analyze_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "analyze_sql" says "analyze": a word for reading.
Description, as the server wrote it Use this when the user wants a complete review of a SQL query. Runs validate, parse, metadata, security, lint, and format concurrently and returns one composite report; hosts that support MCP Apps render it as an interactive report.
Annotations the server declares
- title: Analyze SQL
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
extract_metadataUse this when the user wants the tables, columns, and functions a SQL query references (e.g.1 finding
Why it is in this group
- The input takes a statement or command to run (input.sql), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "extract_metadata" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
Description, as the server wrote it Use this when the user wants the tables, columns, and functions a SQL query references (e.g. for lineage or impact analysis). Returns {tables, columns, functions}.
Annotations the server declares
- title: Extract SQL metadata
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
format_sqlUse this when the user wants SQL pretty-printed or reformatted: one clause per line, optional upper-case keywords and trailing semicolon.1 finding
Why it is in this group
- The input takes a statement or command to run (input.sql), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "format_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
Description, as the server wrote it Use this when the user wants SQL pretty-printed or reformatted: one clause per line, optional upper-case keywords and trailing semicolon. Comments are preserved; unplaceable optimizer hints are refused. Returns {formatted_sql, options}.
Annotations the server declares
- title: Format SQL
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
lint_sqlUse this when the user wants SQL style feedback.1 finding
Why it is in this group
- The input takes a statement or command to run (input.sql), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "lint_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
Description, as the server wrote it Use this when the user wants SQL style feedback. Applies the same 10 rules as `gosqlx lint`: L001 trailing whitespace, L002 mixed indentation, L003 consecutive blank lines, L004 indentation depth, L005 line length (>100), L006 column alignment, L007 keyword case (upper), L008 comma placement (trailing), L009 aliasing consistency, L010 redundant whitespace. Returns {violation_count, violations}.
Annotations the server declares
- title: Lint SQL
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
parse_sqlUse this when the user wants to know how SQL parses: returns an AST summary with the statement count and the type of each statement, optionally for a specific dialect.1 finding
Why it is in this group
- The input takes a statement or command to run (input.sql), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "parse_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
Description, as the server wrote it Use this when the user wants to know how SQL parses: returns an AST summary with the statement count and the type of each statement, optionally for a specific dialect. GO batch separators are excluded from the count.
Annotations the server declares
- title: Parse SQL
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
security_scanUse this when the user wants SQL checked for injection patterns: tautologies, UNION attacks, stacked queries, comment bypasses, and more.1 finding
Why it is in this group
- The input takes a statement or command to run (input.sql), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "security_scan" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
Description, as the server wrote it Use this when the user wants SQL checked for injection patterns: tautologies, UNION attacks, stacked queries, comment bypasses, and more. Returns findings with severity counts.
Annotations the server declares
- title: Scan SQL for injection
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
validate_sqlUse this when the user wants to know whether a SQL statement is syntactically valid, optionally for a specific dialect.1 finding
Why it is in this group
- The name "validate_sql" says "validate": a word for reading.
- The input takes a statement or command to run (input.sql), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "validate_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "validate_sql" says "validate": a word for reading.
Description, as the server wrote it Use this when the user wants to know whether a SQL statement is syntactically valid, optionally for a specific dialect. Returns {valid: bool, error?: string, dialect?: string}.
Annotations the server declares
- title: Validate SQL
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:24 UTC, unchanged since Oct 23, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.gosqlx.dev/mcp: tools/list returned 7 tools to an anonymous client, including analyze_sql (write), extract_metadata (write), format_sql (write), lint_sql (write), parse_sql (write) and 2 more
Findings
Matches of fixed checks, with the text they matched.
- Warnanalyze_sql
The server marks "analyze_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "analyze_sql" says "analyze": a word for reading.
- Warnextract_metadata
The server marks "extract_metadata" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
- Warnformat_sql
The server marks "format_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
- Warnlint_sql
The server marks "lint_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
- Warnparse_sql
The server marks "parse_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
- Warnsecurity_scan
The server marks "security_scan" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.sql), which can change anything it can reach.
Show 1 more findingShow fewer
- Warnvalidate_sql
The server marks "validate_sql" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "validate_sql" says "validate": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:format_sqlChanges thingsdescriptioninputSchema
- Changed:parse_sqlChanges thingsdescriptioninputSchema
Install
Pinned to version 1.17.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http gosqlx https://mcp.gosqlx.dev/mcpclaude mcp add --transport http gosqlx https://mcp.gosqlx.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__gosqlx__analyze_sql",
"mcp__gosqlx__extract_metadata",
"mcp__gosqlx__format_sql",
"mcp__gosqlx__lint_sql",
"mcp__gosqlx__parse_sql",
"mcp__gosqlx__security_scan",
"mcp__gosqlx__validate_sql"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as gosqlx. Review it before you use it.
Capability tags behind 1 rule
- mcp__gosqlx__analyze_sql private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.ajitpratap0/gosqlx/verify?hash=afa7c04015e34a46a8aa7eb8c66fe251be90c841de4645b6ff35544fb5adda00" | jq -e '.changed == false'Pinned hash afa7c04015e3, from Nov 13, 2026, 11:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.ajitpratap0/gosqlx/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.ajitpratap0/gosqlx)Source: MCP Registry · repository. Synced Oct 31, 2026, 14:17 UTC.
GoSQLX MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the GoSQLX MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 7 of which can change, send or delete something, and 7 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the GoSQLX MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the GoSQLX MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the GoSQLX MCP server have?
- 7 tools: 7 write. analyze_sql, extract_metadata, format_sql, lint_sql, parse_sql, security_scan and validate_sql.
Does the GoSQLX MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the GoSQLX MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the GoSQLX MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Oct 31, 2026. Every change is on this page and in its Atom feed.