dbridge-mcp
Read-only MCP server that lets AI agents safely query SQLite, PostgreSQL, and MySQL/MariaDB. Enforces read-only transactions with column masking, row caps, query timeouts, EXPLAIN-based cost rejection, and rate limiting.
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
ugurcl
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.
list_tablesLists every table in the connected database. Call this first to discover what data is available.
describe_tableReturns the columns of a table (name, type, nullability). Use it before writing a query.
sample_tableReturns the first rows of a table as a quick preview, to understand the data before querying.
count_rowsReturns the exact number of rows in a table.
run_queryRuns a single read-only SELECT or WITH statement and returns the rows as JSON. Writes are rejected and results are capped.
explain_queryReturns the query plan and estimated cost without running the query. Use it to check a query is cheap before running it.
column_statsReturns per-column cardinality (distinct values) and null fraction for a table. Use it to judge whether a column is selective enough to be worth indexing or grouping by.
index_healthLists indexes with their columns, size, and scan counts, flagging unused, duplicate, and invalid indexes. Use it to spot dead weight before recommending a new index.
test_indexSimulates a CREATE INDEX without building it (PostgreSQL with the hypopg extension) and reports whether the planner would use it for a given query, with before/after cost estimates. Use this to validate an index idea before recommending it.
slow_queriesReturns the most expensive statements recorded by the database (PostgreSQL pg_stat_statements, MySQL performance_schema), with call counts and total/mean times. Use it to decide what is worth optimizing.
get_limitsReturns the safety limits in effect (row cap, timeout, cost/rate limits, hidden and masked columns, table allow/block lists).
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
DBRIDGE_CONFIG"env": { "": "/absolute/path/to/dbridge.config.json" }DBRIDGE_DB_PATHPass the connection string via the environment variable instead of the command line, so the password does not appear in the process list.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
11/11 tools missing one or more hints — list_tables (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); describe_table (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); sample_table (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 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
9/11 tool handlers declare input schemas (82%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 0/11 tool handlers wrap calls in try/catch (0%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tool test coverage
5/11 tools referenced in tests (45%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
1 child_process call — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (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/ugurcl/dbridge-mcp)?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