DB Explorer
PYPI · DB-EXPLORER-MCP-SERVER
Read-only SQL for PostgreSQL, MySQL and SQLite: schema, safe SELECTs, EXPLAIN, index advice
Available components
Last scanned (3 hours ago)
Scores higher than 67% of PyPI servers
Category Databases
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
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 2 of 41 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 2 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability71
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1120 tokens (~160/item across 7 items; 7 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 Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
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
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_query" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
- An AI judge read all 8 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 21 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 20 Oct 26 53
First indexed and scored.
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 23 Oct 2026 · Analysed pypi/db-explorer-mcp-server@0.1.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 41 packages
| Packages resolved | 41 |
|---|---|
| Stale | 1 |
| No linked repository | 1 |
| 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 →
execute_query Execute Query ~136
Run one read-only SELECT and return its rows. The result is capped by row_limit and by size. truncated=true means more rows exist: filter with WHERE or aggregate rather than raising row_limit. Repeated column names come back labelled name:1, name:2; alias them in the query.
| Name | Type | Req | Description |
|---|---|---|---|
| row_limit | integer | – | Most rows to return, at least 1. Values above 1000 are treated as 1000. |
| sql | string | yes | One SELECT statement (WITH ... SELECT is fine), in the dialect explore_schema reports. No comments, no second statement, no FOR UPDATE or FOR SHARE. |
Structured output declared, but exposes no named fields.
No examples provided.
explain_query Explain Query ~59
Return the database's execution plan for one SELECT, without running it.
| Name | Type | Req | Description |
|---|---|---|---|
| sql | string | yes | One SELECT statement (WITH ... SELECT is fine), in the dialect explore_schema reports. No comments, no second statement, no FOR UPDATE or FOR SHARE. |
Structured output declared, but exposes no named fields.
No examples provided.
explore_schema Explore Schema ~291
List the database's tables and views, or describe one in detail. Every result names the SQL dialect to write queries in. Table and column comments stored in the database come with table_name or detail=true, not with the default listing. CHECK constraints, triggers and view definitions are never included, so their absence here says nothing about the database. A listing comes in pages. A page can hold fewer tables than limit when it reaches the size cap, so continue with offset=next_offset, never offset+limit.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | boolean | – | List each table with its columns, keys and indexes instead of a column count. Use this, not one table_name call per table, when a question touches several tables. Pages get larger, so narrow a big sc… |
| include_sample_data | boolean | – | With table_name, also return 3 sample rows. |
| limit | integer | – | Tables per page, 1 to 1000. |
| name_pattern | – | – | Filter tables by name, case-insensitive. Plain text matches a substring ('order'); *, ? and [] make it a glob ('order_*'). |
| offset | integer | – | Tables to skip. Pass the previous page's next_offset. |
| table_name | – | – | Exact name of one table or view. Returns its columns, keys and indexes, plus a row count for a table; the listing parameters are ignored. |
Structured output declared, but exposes no named fields.
No examples provided.
migration_context Migration Context ~120
Return dialect and one page of table detail for client-side migration drafting. A page can hold fewer tables than limit when it reaches the size cap, so continue with offset=next_offset, never offset+limit.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Tables per page, 1 to 1000. |
| name_pattern | – | – | Filter tables by name, case-insensitive. Plain text matches a substring ('order'); *, ? and [] make it a glob ('order_*'). |
| offset | integer | – | Tables to skip. Pass the previous page's next_offset. |
Structured output declared, but exposes no named fields.
No examples provided.
suggest_index Suggest Index ~119
Suggest indexes for one table or one query. With table_name, returns a CREATE INDEX for each foreign key no index covers. With query, reports the full table scans in its plan, without generated SQL. Nothing is created: the caller decides whether to run a suggestion.
| Name | Type | Req | Description |
|---|---|---|---|
| query | – | – | One SELECT whose plan to check for full table scans, under the same rules as execute_query. Pass this or table_name, not both. |
| table_name | – | – | A table whose foreign keys to check for a covering index. Pass this or query, not both. |
Structured output declared, but exposes no named fields.
No examples provided.
validate_migration Validate Migration ~92
Check migration scripts without executing them. Reports each statement's type and rejects SELECT, comments and unbalanced parentheses. It does not check syntax: the database reports other errors when the script is run.
| Name | Type | Req | Description |
|---|---|---|---|
| down_sql | string | yes | Statements that undo up_sql, in the same form. |
| up_sql | string | yes | Statements that apply the change, separated by semicolons, with no comments. |
Structured output declared, but exposes no named fields.
No examples provided.
validate_schema Validate Schema ~135
Check tables for missing primary keys, unindexed foreign keys, very wide tables and tables with no indexes. A page of tables leaves views out.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Tables per page, 1 to 1000. |
| name_pattern | – | – | Filter tables by name, case-insensitive. Plain text matches a substring ('order'); *, ? and [] make it a glob ('order_*'). |
| offset | integer | – | Tables to skip. Pass the previous page's next_offset. |
| table_name | – | – | One table to check; a view is refused as not found. Omit it to check a page of tables. |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the DB Explorer MCP server?
DB Explorer runs locally as a PyPI package, launched with uvx db-explorer-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · db-explorer-mcp-server
claude mcp add ayush-148-db-explorer-mcp-server -- uvx db-explorer-mcp-server
What is the DB Explorer MCP server?
DB Explorer is an MCP server listed in the public MCP registry as io.github.AYUSH-148/db-explorer-mcp-server. Read-only SQL for PostgreSQL, MySQL and SQLite: schema, safe SELECTs, EXPLAIN, index advice. This page covers its PyPI package (db-explorer-mcp-server).
Is the DB Explorer MCP server safe to use?
DB Explorer scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. 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 DB Explorer MCP server expose?
DB Explorer exposes 7 tools: explore_schema, execute_query, explain_query, validate_schema, suggest_index, and 2 more. Their descriptions and schemas cost roughly 952 tokens of context every time the server is loaded.
Is the DB Explorer MCP server still maintained?
DB Explorer is still listed as active in the MCP registry. We last reached this channel on 23 October 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 DB Explorer MCP server under?
DB Explorer declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.