Chroma’s official MCP server: vector search and collection management for RAG workflows.
sqlglass is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
SQL Server / Azure SQL for agents: real schema, lint, read-only runs, plans, write previews.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user sqlglass-mcp '--' uvx sqlglass
# 2 — ask your agent for something these tools do
# list_connections, refresh_schema, list_tables and 26 more
sqlglass costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts sqlglass as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user sqlglass-mcp '--' uvx sqlglassReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take SQLGLASS_CONFIG (Path to sqlglass.toml (connection definitions). Optional if the file is in the workspace or the user data folder.) if you want to set it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
29 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List the configured database connections (from sqlglass.toml), which is the default, where the query
No parameter schema on file.
Re-read tables, views, columns, keys, indexes and foreign keys from the database into the local cache.
No parameter schema on file.
List tables and views with row counts and descriptions. Filter by schema name and/or a name pattern
No parameter schema on file.
Columns (type, nullability, identity/computed), primary key, indexes, foreign keys in both directions and
No parameter schema on file.
Find tables and columns whose name contains the text (or matches a * ? wildcard pattern), plus tables whose
No parameter schema on file.
How two tables relate: the shortest chain of declared foreign keys between them, as ready-to-use JOIN lines.
No parameter schema on file.
No parameter schema on file.
Check a query for correctness traps (NOT IN + NULLs, LEFT JOIN turned INNER by WHERE, join without ON,
No parameter schema on file.
What a query touches: tables/views, columns per table, CTEs, parameters and its output columns.
No parameter schema on file.
Pretty-print T-SQL in one canonical style. Normalises cosmetics (adds AS to aliases, rewrites
No parameter schema on file.
Translate a query between dialects (tsql, postgres, mysql, sqlite, snowflake, bigquery, databricks, oracle,
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Generate a CREATE OR ALTER VIEW script (TEXT ONLY -- never executed here) from a SELECT or a library query.
No parameter schema on file.
Run a read-only query and return the first rows. Give either inline 'sql' or a library 'query' (id or name).
No parameter schema on file.
Estimated execution plan, summarised: the expensive operators, scans on big tables, key lookups, sorts,
No parameter schema on file.
No parameter schema on file.
A few rows of a table or view, to see what the values actually look like.
No parameter schema on file.
Per-column row count, NULLs, distinct values, min and max, in one aggregate query. Use it to learn a
No parameter schema on file.
Browse the saved-query library. 'search' matches id, name, description and the SQL text; 'tag' filters by tag.
No parameter schema on file.
One saved query: header fields, parameters, the SQL, what tables it touches, and lint findings.
No parameter schema on file.
No parameter schema on file.
Remove a query from the library. Its text is kept in a snapshot, so restore_snapshot brings it back.
No parameter schema on file.
Impact analysis: which saved queries read a given table/view (and optionally a given column of it).
No parameter schema on file.
Lint every saved query (against each query's cached connection schema when available). Catches queries
No parameter schema on file.
No parameter schema on file.
Turn a hard-coded value in a saved query into a parameter: every occurrence of the literal ('2026-01-01', 100)
No parameter schema on file.
Before-images taken automatically ahead of every library write, newest first.
No parameter schema on file.
Put the queries in a snapshot back to how they were before that write ('latest' = undo the last write).
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install sqlglass or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (29 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_connections | no tags | |
| refresh_schema | no tags | |
| list_tables | no tags | |
| describe_table | no tags | |
| search_schema | no tags | |
| find_join_path | no tags | |
| build_select | no tags | |
| lint_sql | no tags | |
| analyze_sql | no tags | |
| format_sql | no tags | |
| translate_sql | no tags | |
| build_create_table | no tags | |
| build_procedure | no tags | |
| build_view | no tags | |
| run_query | no tags | |
| explain_query | no tags | |
| preview_write | no tags | |
| sample_table | no tags | |
| profile_table | no tags | |
| list_queries | untrusted-input | untrusted-input: keyword "browse" |
| get_query | no tags | |
| save_query | no tags | |
| delete_query | state-write | state-write: declares destructiveHint: true |
| find_usage | no tags | |
| lint_library | no tags | |
| rename_in_library | no tags | |
| extract_parameter | no tags | |
| list_snapshots | no tags | |
| restore_snapshot | state-write | state-write: declares destructiveHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish sqlglass can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.