io.github.YimingYAN/fivetran-mcp
PYPI · FIVETRAN-MCP · SCANNED SEP 20
MCP server for Fivetran API - manage syncs, check status, and control data pipelines
Available components
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 native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 23 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- 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
- License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 230 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability82
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1180 tokens (~78/item across 15 items; 15 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 15 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
How do I install the io.github.YimingYAN/fivetran-mcp server?
io.github.YimingYAN/fivetran-mcp runs locally as a PyPI package, launched with uvx fivetran-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · fivetran-mcp
claude mcp add yimingyan-fivetran-mcp -- uvx fivetran-mcp
{
"mcpServers": {
"yimingyan-fivetran-mcp": {
"command": "uvx",
"args": [
"fivetran-mcp"
]
}
}
} {
"servers": {
"yimingyan-fivetran-mcp": {
"command": "uvx",
"args": [
"fivetran-mcp"
]
}
}
} codex mcp add yimingyan-fivetran-mcp -- uvx fivetran-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"yimingyan-fivetran-mcp": {
"type": "local",
"command": [
"uvx",
"fivetran-mcp"
],
"enabled": true
}
}
} openclaw mcp add yimingyan-fivetran-mcp --command uvx --arg fivetran-mcp
mcp_servers:
yimingyan-fivetran-mcp:
command: "uvx"
args: ["fivetran-mcp"] {
"McpServers": {
"yimingyan-fivetran-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"fivetran-mcp"
]
}
}
} assistant mcp add yimingyan-fivetran-mcp -t stdio -c uvx -a fivetran-mcp
{
"mcpServers": {
"yimingyan-fivetran-mcp": {
"command": "uvx",
"args": [
"fivetran-mcp"
]
}
}
} 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.
- 19 Sept 26 −2
- Stability: pass → 0.83 functional
- 18 Sept 26 0
- Stability: 0.97 → pass security
- 17 Sept 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.
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −3
- Stability: pass → 0.80 functional
- 11 Sept 26 0
- Stability: 0.97 → pass security
- 10 Sept 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.
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 20 Sept 2026 · Analysed pypi/fivetran-mcp@0.3.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
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 23 packages
| Packages resolved | 23 |
|---|---|
| Stale | 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 →
get_connection_schema Get Connection Schema ~139
Retrieve schema information for a Fivetran connection with optional table filter. When called without a table parameter, returns all schemas and tables. When a table is specified (format: "schema.table_name"), returns detailed information for that specific table including all column metadata. This is useful for: - Debugging dbt model failures when columns are missing - Detecting schema changes - Building new models with accurate column metadata - Identifying which columns are actively synced vs excluded
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
| table | – | – | Optional table name in "schema.table_name" format to get detailed info |
Structured output declared, but exposes no named fields.
No examples provided.
get_connection_status Get Connection Status ~65
Get detailed status for a specific Fivetran connection. Returns comprehensive information including sync state, tasks with full details, warnings, and scheduling configuration. Use this for investigating connection issues and understanding sync status.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
Structured output declared, but exposes no named fields.
No examples provided.
get_schema Get Schema ~67
Retrieve the complete schema configuration for a Fivetran connection. Returns all schemas and tables with their enabled/disabled status, sync modes, and configuration. Useful for understanding what data is being synced and investigating missing tables.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
Structured output declared, but exposes no named fields.
No examples provided.
get_table_columns Get Table Columns ~115
Retrieve column details for a specific table in a Fivetran connection. Returns column names, sync configuration, and metadata. Useful for investigating schema issues or understanding table structure. Note: Column data types are not available via the Fivetran API. Data types can be queried directly from your destination database.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
| schema | string | yes | The schema name containing the table |
| table | string | yes | The table name to get columns for |
Structured output declared, but exposes no named fields.
No examples provided.
get_table_status Get Table Status ~181
Get per-table sync status for a Fivetran connection. Returns detailed status for each table including enabled/disabled state, sync configuration, and metadata from the most recent successful sync. Useful for debugging large connectors with many tables, identifying stale tables, and monitoring data freshness. For connectors with many tables (e.g., Airtable with 20+ bases, or Postgres with 50+ tables), this provides visibility into which specific tables are configured and their sync settings. Note: Table metadata (like destination names) is only available after at least one successful sync has completed.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
| enabled_only | boolean | – | If True, only return tables that are enabled for sync |
| schema_filter | – | – | Optional schema name to filter tables (e.g., "public") |
Structured output declared, but exposes no named fields.
No examples provided.
list_connections List Connections ~55
List all Fivetran connections in the account.
| Name | Type | Req | Description |
|---|---|---|---|
| group_id | – | – | Optional group ID to filter connections by group |
| limit | integer | – | Maximum number of connections to return (1-1000, default 100) |
Structured output declared, but exposes no named fields.
No examples provided.
list_groups List Groups ~54
List all Fivetran groups (destinations) in the account. Groups represent destinations where data is synced to.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of groups to return (1-1000, default 100) |
Structured output declared, but exposes no named fields.
No examples provided.
list_tables List Tables ~69
List all tables in a Fivetran connection with their sync status. Provides a flattened view of all tables across all schemas, showing enabled status, sync mode, and configuration. Useful for quickly seeing which tables are being synced.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
Structured output declared, but exposes no named fields.
No examples provided.
pause_connection Pause Connection ~39
Pause a Fivetran connection. Paused connections will not sync data until resumed.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
Structured output declared, but exposes no named fields.
No examples provided.
reload_schema Reload Schema ~63
Reload the schema configuration from the source for a Fivetran connection. Fetches the latest schema from the data source and updates the configuration. Useful after source schema changes to detect new tables or columns.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
Structured output declared, but exposes no named fields.
No examples provided.
resume_connection Resume Connection ~41
Resume a paused Fivetran connection. The connection will start syncing according to its schedule.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
Structured output declared, but exposes no named fields.
No examples provided.
resync_tables Resync Tables ~93
Trigger a historical resync for specific tables within a connection. This re-syncs historical data only for the specified tables, not the entire connection. Useful when you need to refresh specific tables without a full resync.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
| tables | array | yes | List of table names to resync (e.g., ["schema.table_name", "public.users"]) |
Structured output declared, but exposes no named fields.
No examples provided.
test_connection Test Connection ~63
Test a Fivetran connection to diagnose connectivity and configuration issues. Executes diagnostic tests to identify root causes when syncs fail, validate connection health proactively, and support incident response workflows.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection to test |
Structured output declared, but exposes no named fields.
No examples provided.
trigger_resync Trigger Resync ~61
Trigger a full historical resync for a Fivetran connection. This re-syncs all historical data from the source. Use with caution as it may take significant time and resources.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
Structured output declared, but exposes no named fields.
No examples provided.
trigger_sync Trigger Sync ~75
Trigger a data sync for a Fivetran connection. This starts a sync without waiting for the next scheduled sync time. Does not override the standard sync frequency.
| Name | Type | Req | Description |
|---|---|---|---|
| connection_id | string | yes | The unique identifier of the connection |
| force | boolean | – | If True, force the sync even if one is already in progress |
Structured output declared, but exposes no named fields.
No examples provided.
What is the io.github.YimingYAN/fivetran-mcp server?
io.github.YimingYAN/fivetran-mcp is listed in the public MCP registry as io.github.YimingYAN/fivetran-mcp. MCP server for Fivetran API - manage syncs, check status, and control data pipelines. This page covers its PyPI package (fivetran-mcp).
Is the io.github.YimingYAN/fivetran-mcp server safe to use?
io.github.YimingYAN/fivetran-mcp scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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 io.github.YimingYAN/fivetran-mcp server expose?
io.github.YimingYAN/fivetran-mcp exposes 15 tools: list_connections, get_connection_status, trigger_sync, trigger_resync, resync_tables, and 10 more. Their descriptions and schemas cost roughly 1,180 tokens of context every time the server is loaded.
Is the io.github.YimingYAN/fivetran-mcp server still maintained?
io.github.YimingYAN/fivetran-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.