- Home
- Skills
- Data & Databases
- FME MCP ULTRA
Works with the AI Agents you already use
FME MCP ULTRA
Automate Safe Software FME GIS pipelines, inspect workspace parameters, and execute spatial ETL tasks.
Free
FME MCP ULTRA
Example session with this skill installed
Scan the /data/workspaces directory, inspect the 'spatial_filter.fmw' workspace, and show me its published parameters and transformers.
- Read your context and instructions
- Compiled the fme mcp ultra
I have scanned the directory and inspected the requested FME workspace. Below is the technical breakdown of the pipeline structure and its configuration options.
FME Workspace Inspection: spatial_filter.fmw
| Attribute | Details |
|---|---|
| Workspace Path | /data/workspaces/spatial_filter.fmw |
| FME Compatibility | 2023.1+ |
| Readers | OGC GeoPackage, Esri Shapefile |
| Writers | PostGIS (Production_DB) |
| Total Transformers | 8 |
Published Parameters
SourceDataset_GEOPACKAGE: Path to the input .gpkg file (Default:C:/data/input.gpkg)Target_Schema: Target PostGIS schema name (Default:public)Buffer_Distance: Numeric value for spatial expansion (Default:100.0)Validation_Level: Choice:Basic,Full,None
Transformer Canvas Topology
- Bufferer: Generates circular buffers based on
Buffer_Distance. - SpatialFilter: Performs intersection tests between source and clip boundaries.
- AttributeKeeper: Removes temporary processing fields.
- GeometryValidator: Checks for self-intersections and null geometries.
- Reprojector: Converts coordinates to
EPSG:2154.
Next steps
- Run a test translation by providing a source path for
SourceDataset_GEOPACKAGE. - Validate the input GeoPackage geometry using
gis_validate_geometrybefore execution. - Update the
Buffer_Distanceparameter to adjust the spatial filter sensitivity.
Connects securely to your tools. The creator never sees your data.
About this skill
Handling spatial data pipelines manually is slow and prone to geometry errors. This skill connects your agent to Safe Software FME, automating the inspection, execution, and validation of GIS ETL pipelines.
What it does
- Workspace discovery scans directories to locate and map
.fmwfiles and their dependencies. - Visual introspection extracts canvas topology to identify transformers, reader/writer types, and port connections.
- Pipeline execution runs local FME Form workspaces or submits enterprise jobs to remote FME Flow instances.
- Spatial geoprocessing performs direct coordinate reprojection, buffer generation, and topology validation.
- Data profiling audits datasets for null values and completeness to generate YAML data contracts.
How it works
- Diagnostic check: Run
fme_diagnoseto verify the FME installation, licensing, andfmeobjectsbindings. - Discovery & Introspection: Use
fme_discover_workspacesandfme_inspect_canvasto understand the pipeline logic and required parameters. - Parameter validation: Retrieve and map published parameters to ensure valid inputs before execution.
- Automated translation: Trigger
fme_run_workspaceand analyze the resulting logs for features read, written, and CPU time. - Quality audit: Generate data quality reports and validate geometries for self-intersections or ring closures.
Frameworks & tools
Specifically designed for Safe Software FME (versions 2018.0 to 2026+), FME Form, and FME Flow. It utilizes the fme-mcp-ultra protocol to bridge FME CLI and Python bindings with AI agents.
Why this beats prompting it yourself
Writing manual scripts to interface with FME's CLI or Python API is tedious and lacks real-time workspace introspection. This skill provides deep visibility into the visual canvas of a workspace, allowing the agent to troubleshoot broken connections or parameter mismatches that generic prompts would miss.
Use cases
- Automate nightly GIS data synchronization between PostGIS and Shapefile formats.
- Batch reproject large coordinate sets between WGS84 and local reference systems like Lambert-93.
- Audit land registry GeoPackages to detect topology errors and missing attributes.
- Inspect legacy FME workspaces to document transformer logic and data flow without opening the FME Workbench UI.
Known limitations
Requires FME Form or FME Flow installed on the host or reachable via network. Workspace execution is subject to local file system permissions and PathGuard directory restrictions.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
Requires FME Form or Flow (2018.0+) installed. Workspace execution depends on local FME licensing and PathGuard directory permissions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 8 days ago
- Free with an Agensi account
- Software
- Fme Ultra MCP