JDBC MCP Server
OCI · GHCR.IO/IGOROLV/JDBC-MCP-SERVER:0.2.0
Read-only SQL, plans, schema for AI agents: PostgreSQL, Oracle, SQL Server, Firebird, SQLite, JDBC
Available components
Last scanned (17 hours ago)
Scores higher than 76% of OCI 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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency48
- 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 (Apache-2.0).Pass
- Actively maintained (last published 56 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 5429 tokens (~110/item across 49 items; 49 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage91
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 67% of tool parameters carry a description.Partial
- Structured output schemas are declared (88% 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; "executeQuery" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
- An AI judge read all 49 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 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.
Checks we ran (12)
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (4)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
- Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
- Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 16 Nov 26 0
- Stability: 0.97 → pass security
- 15 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 8 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 6 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.
- 4 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.
- 3 Nov 26 −6
- Stability: pass → 0.57 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 21 Nov 2026 · Analysed oci/ghcr.io/igorolv/jdbc-mcp-server:0.2.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
searchObjects ~104
Find database objects when only a full or partial name is known. Searches non-system tables, views, routines, packages, sequences and synonyms case-insensitively; use describeTable after finding a table or view whose structure is needed.
| Name | Type | Req | Description |
|---|---|---|---|
| connection | string | yes | Database to run against. Call listConnections for valid names; do not guess. |
| namePattern | string | yes | Name pattern — plain substring (auto-wrapped in %..%) or explicit pattern with % / _ |
| Name | Type | Req | Description |
|---|---|---|---|
| objects | array|null | – | Matching database objects across tables, views, routines, sequences, and synonyms. |
No examples provided.
tableContext ~156
Explore the relationship neighborhood of one known table: compact root/nearby table metadata plus declared FK and optional observed join edges. Use when nearby joins are needed; for only the table's own fields or structure, use describeTable.
| Name | Type | Req | Description |
|---|---|---|---|
| connection | string | yes | Database to run against. Call listConnections for valid names; do not guess. |
| depth | integer | – | FK depth (default 1). |
| includeIncoming | boolean | – | Include child references (default true). |
| includeObserved | boolean | – | Include declared/observed/semantic usage evidence (default: catalog enabled). |
| includeStats | boolean | – | Include row/size/activity stats (default false). |
| schema | string | – | – |
| table | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| depth | integer|null | yes | Relationship expansion depth from the root object. |
| includeIncoming | boolean|null | yes | True when tables that reference the root table were included. |
| includeObserved | boolean|null | yes | True when usage-catalog observed joins were included as relationship evidence. |
| includeStats | boolean|null | yes | True when live table statistics were requested for context tables. |
| relationships | array|null | – | Relationship edges relevant to the context, graph, or observed-relationships result. |
| rootSchema | string|null | – | Schema of the root table requested for table context. |
| rootTable | string|null | – | Root table requested for table context. |
| tables | array|null | – | Tables included in this context, graph, query inspection, or usage record. |
No examples provided.
tableStats ~89
Inspect operational size and activity statistics for one known table: estimated/live rows, storage, dead tuples, maintenance times and scan counters. For fields, keys and constraints, use describeTable; available statistics depend on engine and privileges.
| Name | Type | Req | Description |
|---|---|---|---|
| connection | string | yes | Database to run against. Call listConnections for valid names; do not guess. |
| schema | string | – | – |
| table | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| avgRowLen | – | – | Average row length reported by optimizer statistics, when available. |
| blocks | – | – | Engine-reported allocated block count, when available. |
| chainCount | – | – | Oracle chained row count, when available. |
| compression | – | – | Compression setting reported for the table, when available. |
| createDate | – | – | SQL Server object creation timestamp, when available. |
| deadTuplePct | – | – | Approximate percentage of dead tuples among total tuples. |
| deadTuples | – | – | Estimated number of dead tuples or obsolete row versions. |
| emptyBlocks | – | – | Engine-reported empty block count, when available. |
| error | string|null | – | Error encountered while loading table statistics; other fields may be partial when set. |
| estimatedRows | – | – | Planner or catalog estimate of rows for this object or operation. |
| found | boolean|null | yes | True when the requested object or path was found. |
| globalStats | – | – | Oracle flag indicating whether global statistics are present. |
| idxScan | – | – | Number of index scans recorded for the table. |
| idxTupFetch | – | – | Number of table tuples fetched through this index, when available. |
| indexesSizeBytes | – | – | Storage used by indexes on the table, in bytes. |
| isFiletable | – | – | SQL Server flag indicating a FileTable. |
| isMemoryOptimized | – | – | SQL Server flag indicating a memory-optimized table. |
| lastAnalyze | – | – | Timestamp of the last manual analyze/statistics collection, when available. |
| lastAnalyzed | – | – | Timestamp when database optimizer statistics were last collected, when available. |
| lastAutoanalyze | – | – | Timestamp of the last automatic analyze/statistics collection, when available. |
| lastAutovacuum | – | – | Timestamp of the last automatic vacuum, when available. |
| lastVacuum | – | – | Timestamp of the last manual vacuum, when available. |
| liveTuples | – | – | Estimated number of live tuples or rows. |
| modifyDate | – | – | SQL Server object modification timestamp, when available. |
| partitioned | – | – | Whether the table is partitioned, when the engine reports it. |
| relkind | – | – | Engine-specific relation kind for the table or view. |
| sampleSize | – | – | Sample size used for optimizer statistics, when available. |
| schema | string|null | – | – |
| segmentBytes | – | – | Oracle segment size in bytes, when segment metadata is accessible. |
| segmentBytesError | string|null | – | Permission or lookup error encountered while reading segment size. |
| seqScan | – | – | Number of sequential scans recorded for the table. |
| seqTupRead | – | – | Number of tuples read by sequential scans. |
| table | string|null | – | – |
| tableSizeBytes | – | – | Storage used by the table heap or base data, in bytes. |
| temporalTypeDesc | – | – | SQL Server temporal table type description. |
| temporary | – | – | Whether the table is temporary, when the engine reports it. |
| toastSizeBytes | – | – | PostgreSQL TOAST storage used by the table, in bytes. |
| totalSizeBytes | – | – | Total storage used by the table, indexes, and auxiliary storage, in bytes. |
| tupDel | – | – | Number of deleted tuples recorded by engine statistics. |
| tupIns | – | – | Number of inserted tuples recorded by engine statistics. |
| tupUpd | – | – | Number of updated tuples recorded by engine statistics. |
| userStats | – | – | Oracle flag indicating whether user-defined statistics are present. |
No examples provided.
timedQuery ~201
Measure one read-only SQL SELECT / WITH / EXPLAIN while still returning its rows and elapsed time. Use executeQuery when timing is irrelevant or benchmarkQuery for repeated cold/warm measurements. Bind '?'->params, ':name'->namedParams; never mix. E.g. :status -> namedParams={status:'PAID'} — key is the bare name. Adds available per-statement counter deltas (calls, execution time, rows, buffer hits/reads).
| Name | Type | Req | Description |
|---|---|---|---|
| connection | string | yes | Database to run against. Call listConnections for valid names; do not guess. |
| limit | integer | – | Row limit (default: the connection's maxRows). |
| namedParams | object | – | Values for ':name' placeholders, keyed by name. |
| params | array | – | Values for '?' placeholders, in order. |
| sql | string | yes | – |
| timeoutSeconds | integer | – | Timeout in seconds (default: the connection's queryTimeoutSeconds). |
| Name | Type | Req | Description |
|---|---|---|---|
| columnTypes | array|null | – | Database type names for the result columns, in the same order as columns. |
| columns | array|null | – | Result column names in output order. |
| elapsedMs | number|null | yes | Wall-clock elapsed time for the query execution, in milliseconds. |
| engine | string|null | – | Database engine that produced the result, such as PostgreSQL, Oracle, SQL Server, Firebird, or SQLite. |
| pgStatStatements | – | – | – |
| rowCount | integer|null | yes | – |
| rows | array|null | – | Returned result rows as column-name to value maps, capped by the requested limit. |
| truncated | boolean|null | yes | True when the configured row or finding cap was reached and more data may exist. |
No examples provided.
unusedIndexes ~94
Find non-PK/non-unique indexes with zero recorded scans as removal candidates. Unlike redundantIndexes, this uses workload counters, which are meaningful only after representative traffic and are not supported by every engine.
| Name | Type | Req | Description |
|---|---|---|---|
| connection | string | yes | Database to run against. Call listConnections for valid names; do not guess. |
| minSizeBytes | integer | – | Minimum size in bytes; omit tiny indexes. |
| schema | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer|null | yes | Number of unused indexes returned. |
| indexes | array|null | – | Indexes available on the table or returned by an index-statistics scan. |
| note | string|null | – | Additional context about support, limits, interpretation, or engine-specific behavior. |
| schema | string|null | – | – |
| supported | boolean|null | yes | True when this tool is supported for the current database engine and privileges. |
No examples provided.
usageCatalogStatus ~65
Check whether the usage catalog is enabled and ready before relying on observed-query or semantic evidence. Returns configured sources, indexing state, counts and load errors without searching for queries.
| Name | Type | Req | Description |
|---|---|---|---|
| connection | string | yes | Database to run against. Call listConnections for valid names; do not guess. |
| Name | Type | Req | Description |
|---|---|---|---|
| catalogEnabled | boolean|null | yes | False when the usage catalog is disabled; true when indexing and lookups are allowed. |
| connection | string|null | – | Name of the connection this catalog belongs to. |
| indexing | boolean|null | yes | True while the usage catalog index is being built. |
| sources | array|null | – | Configured usage-catalog source paths and database-native sources considered for indexing. |
| state | string|null | – | Current usage-catalog index state, such as not_started, indexing, ready, or failed. |
No examples provided.
validateQuery ~165
Check whether the database driver accepts a SELECT / WITH / EXPLAIN without executing it: prepares the statement and validates parameters, syntax and referenced objects. Use inspectQuery for parser-only AST inspection or queryLint for advisory metadata/index warnings. Bind '?'->params, ':name'->namedParams; never mix. E.g. :status -> namedParams={status:'PAID'} — key is the bare name.
| Name | Type | Req | Description |
|---|---|---|---|
| connection | string | yes | Database to run against. Call listConnections for valid names; do not guess. |
| namedParams | object | – | Named parameters for ':name' placeholders. Required when SQL contains ':name'. |
| params | array | – | Positional parameters for '?' placeholders, in order. Required when SQL contains '?'. |
| sql | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| columns | integer|null | – | Number of result columns reported by driver validation when available. |
| error | string|null | – | – |
| inspection | object|null | – | Parsed query inspection that underpins validation (opaque; the inspectQuery tool returns the typed form). |
| parameters | integer|null | – | Number of SQL parameters expected or validated. |
| stage | string|null | – | Validation stage that failed, such as guard, params, or driver. |
| valid | boolean|null | yes | True when the statement passed guard, parameter, and driver validation. |
No examples provided.
How do I install the JDBC MCP Server server?
JDBC MCP Server runs locally as a container image, launched with docker run --rm -i -e JDBC_MCP_RESOURCES_ENABLED ghcr.io/igorolv/jdbc-mcp-server:0.2.0, plus the required --mount, which you supply. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/igorolv/jdbc-mcp-server:0.2.0
claude mcp add igorolv-jdbc-mcp-server -- docker run --rm -i -e JDBC_MCP_RESOURCES_ENABLED ghcr.io/igorolv/jdbc-mcp-server:0.2.0
This image reads JDBC_MCP_RESOURCES_ENABLED. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --mount as required and gives no value we can show, so it is not in this command. Add it before you run it.
What is the JDBC MCP Server server?
JDBC MCP Server is listed in the public MCP registry as io.github.igorolv/jdbc-mcp-server. Read-only SQL, plans, schema for AI agents: PostgreSQL, Oracle, SQL Server, Firebird, SQLite, JDBC. This page covers its container image (ghcr.io/igorolv/jdbc-mcp-server:0.2.0).
Is the JDBC MCP Server server safe to use?
JDBC MCP Server scores 51 out of 100 on VerifyMCP. 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 JDBC MCP Server server expose?
JDBC MCP Server exposes 49 tools: rebuildCatalog, benchmarkQuery, timedQuery, listConnections, columnDistribution, and 44 more. Their descriptions and schemas cost roughly 5,429 tokens of context every time the server is loaded.
Is the JDBC MCP Server server still maintained?
JDBC MCP Server is still listed as active in the MCP registry. We last reached this channel on 21 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 JDBC MCP Server server under?
JDBC MCP Server 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.
What did VerifyMCP test on the JDBC MCP Server server?
VerifyMCP ran 12 checks on JDBC MCP Server, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about JDBC MCP Server: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.