io.github.orifisher2/sqlike-mcp
NPM · @SQLIKE/MCP
Lints SQL and checks rewrites return the same rows. Postgres, MySQL, MariaDB, SQLite, MSSQL, DuckDB
Available components
Last scanned (19 hours ago)
Scores higher than 93% of npm servers
Category Testing and QA
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 0 of 5 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to orifisher2/sqlike). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 7 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability62
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1223 tokens (~611/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
- Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 +16
- Malware scan: unverified → pass ▲ security
- 27 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- Security disclosure: unverified → pass ▲ functional
- Package version: 0.2.2 → 0.2.3 functional
- 26 Oct 26 0
- Security disclosure: pass → unverified ▼ functional
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 +4
- Stability: unverified → 0.27 ▲ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed npm/@sqlike/mcp@0.2.3
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | orifisher2/sqlike |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/orifisher2/sqlike/.github/workflows/release-mcp.yml@refs/tags/mcp-v0.2.3 |
| Rekor log index | 3522584051 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:746cbabaaaad55d0ab62fba44953e7531be12f8924adadb12dd480476575767afa0def83f5bcd6b0aba3a2c2d0e8850109c86ab13e9e6614474a0825a |
Background: How many MCP packages publish verified provenance →
Dependencies 5 packages
| Packages resolved | 5 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
analyze ~553
Use when you write, edit, or review a SQL query and want it checked before it runs. Returns SQLike's deterministic analysis as a JSON envelope: validity errors, anti-patterns, safe rewrites, and schema/index advice. Pass optional schema DDL for column- and type-aware checks, table row counts (stats) so severity follows volume, an EXPLAIN plan so index findings are confirmed or dismissed by what the planner did, and dialect (postgres default, mysql, mariadb, sqlite, mssql, duckdb — DuckDB is columnar, so its severities and index advice differ). The query is tokenized locally before it leaves the machine — identifiers and literals are masked. A query that does not parse is answered locally, with a parse-error finding that names the mistake, or names the construct SQLike does not support yet and says the query is valid, and sends nothing. A query holding a name that can't be masked makes the tool refuse rather than send raw SQL; on that refusal, ask the user whether to send the raw query, and only then call again with allow_raw=true
| Name | Type | Req | Description |
|---|---|---|---|
| allow_raw | boolean | – | Only matters when the query can't be tokenized/privacy-masked — it didn't parse locally, or it holds a name that can't be masked. Set true to send the RAW SQL to the server anyway. Default false bloc… |
| dialect | string|null | – | SQL dialect: "postgres" (default), "mysql", "sqlite", "mssql", "mariadb", or "duckdb". |
| explain | string|null | – | Optional query plan, to confirm or dismiss missing-index findings by what the planner actually did and, with actual row counts, re-score every performance finding: Postgres `EXPLAIN (ANALYZE, FORMAT… |
| schema | string|null | – | Optional schema DDL (CREATE TABLE / CREATE INDEX) for column- and type-aware checks. |
| sql | string | yes | The SQL query to analyze. |
| stats | string|null | – | Optional table row counts as a JSON map, e.g. `{"orders": 2000000}`. Severity scales with volume: a large table promotes a performance finding, a small one demotes it and drops index advice. Table na… |
No output schema declared.
No examples provided.
diff ~303
Use to confirm two SQL queries are equivalent — whenever you rewrite, refactor, or optimize a query and need to prove it still returns the same results (something an LLM cannot reliably self-grade). Returns SQLike's deterministic JSON verdict: an overall result (Equivalent / EquivalentWithNotes / Differs / Undecided / NotComparable), a confidence level, and a per-property report (columns, rows, cardinality, order). Undecided never means equivalent. If one query is invalid (a missing table or column, an ambiguous reference) the pair is Differs, since a query that does not run cannot return the same rows as one that does; if both are invalid it is NotComparable, with a reason for each. A query that does not parse is refused with the reason: the mistake, or the construct SQLike does not support yet. Both queries share one optional schema DDL; dialect is postgres default, mysql, mariadb, sqlite, mssql, duckdb.
| Name | Type | Req | Description |
|---|---|---|---|
| dialect | string|null | – | SQL dialect: "postgres" (default), "mysql", "sqlite", "mssql", "mariadb", or "duckdb". |
| schema | string|null | – | Optional schema DDL both queries resolve against (one schema — comparing over different schemas is ill-posed). |
| sql_a | string | yes | The original query. |
| sql_b | string | yes | The rewritten query to check for equivalence against `sql_a`. |
No output schema declared.
No examples provided.
How do I install the io.github.orifisher2/sqlike-mcp server?
io.github.orifisher2/sqlike-mcp runs locally as an npm package, launched with npx -y @sqlike/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @sqlike/mcp
claude mcp add orifisher2-sqlike-mcp -- npx -y @sqlike/mcp
What is the io.github.orifisher2/sqlike-mcp server?
io.github.orifisher2/sqlike-mcp is listed in the public MCP registry as io.github.orifisher2/sqlike-mcp. Lints SQL and checks rewrites return the same rows. Postgres, MySQL, MariaDB, SQLite, MSSQL, DuckDB. This page covers its npm package (@sqlike/mcp).
Is the io.github.orifisher2/sqlike-mcp server safe to use?
io.github.orifisher2/sqlike-mcp scores 89 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.orifisher2/sqlike-mcp server expose?
io.github.orifisher2/sqlike-mcp exposes 2 tools: analyze, diff. Their descriptions and schemas cost roughly 856 tokens of context every time the server is loaded.
Is the io.github.orifisher2/sqlike-mcp server still maintained?
io.github.orifisher2/sqlike-mcp is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.orifisher2/sqlike-mcp server under?
io.github.orifisher2/sqlike-mcp declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.