MCP SQL Server
Enables AI assistants to explore SQL Server schemas, relationships, and execute safe SQL queries with read-only mode by default and optional write control.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
WendellOttoni
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
current_connectionShow the active SQL Server connection, permissions, and metadata cache status
list_databasesList databases accessible on the current SQL Server
list_schemasList all schemas in the database
list_tablesList all tables and views in the database, grouped by schema
find_tablesSearch for tables and views by name (partial match)
describe_tableShow columns, data types, primary keys, foreign keys, check constraints, and identity/computed info of a table
list_indexesList all indexes of a table, including key columns and included columns
table_statsShow row count, disk size, and dates for a table
find_columnsSearch for columns by name across all tables (useful to find where a field is used)
relationship_mapShow all foreign key relationships in a schema - useful to understand the full data model
list_proceduresList stored procedures and functions in the database
queryswitch_databaseSwitch the active database for the current MCP session without restarting the server
switch_portSwitch the active SQL Server port for the current MCP session without restarting the server
switch_credentialsSwitch the SQL Server login credentials for the current MCP session without restarting the server. Leave user empty to use Windows authentication.
switch_connectionSwitch port, user, password, and database together for the current MCP session with a single reconnect at the end.
permissionsShow the current permission mode: allowed/blocked operations, table and schema restrictions
sample_valuesReturn sample distinct values for one or more columns of a table
query_with_explanationExecute a read query and return both rows and a short interpretation
refresh_metadataReload metadata cache from the database
healthShow connection state, cache status, and runtime metrics
find_entitiesSearch tables by intent using names, columns, descriptions, aliases, and relationship signals
schema_summarySummarize schemas, central tables, and probable hotspots in the catalog
explain_tableExplain the likely role of a table based on names, columns, descriptions, and relationships
suggest_join_pathFind a join path between two tables using the foreign-key graph
plan_queryPlan a query from a natural-language goal using entity ranking and join-path suggestions
validate_queryAnalyze a SQL statement before execution and report operation, tables, risk, and warnings
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
27/27 tools missing one or more hints — current_connection (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_databases (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_schemas (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +24 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
19/27 tool handlers declare input schemas (70%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 8/27 tool handlers wrap calls in try/catch (30%)
Wrap each tool handler body in try/catch and return a structured error response.
Tool test coverage
8/27 tools referenced in tests (30%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/wendellottoni/mcp-sqlserver)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check