update docs

Author: i-norden

README.md

@@ -1,6 +1,6 @@
 # roteiro-agent
 
-MCP (Model Context Protocol) server for [Roteiro](roteiro.io) — a spatial data platform. Enables AI agents (Claude Desktop, VS Code, Cursor) to work with geospatial datasets, run geoprocessing operations, execute PostGIS queries, and more.
+MCP (Model Context Protocol) server for Roteiro, a spatial data platform. Enables AI agents (Claude Desktop, VS Code, Cursor) to work with geospatial datasets, run geoprocessing operations, execute SQL, and more.
 
 ## Installation
 
@@ -41,9 +41,9 @@ Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:
 ```json
 {
   "mcpServers": {
-    "cairn": {
+    "roteiro": {
       "command": "roteiro-agent",
-      "args": ["--server-url", "https://your-cairn-instance.com", "--api-key", "cairn_abc123"]
+      "args": ["--server-url", "https://your-roteiro-instance.com", "--api-key", "roteiro_abc123"]
     }
   }
 }
@@ -56,9 +56,9 @@ Add to `.vscode/mcp.json`:
 ```json
 {
   "servers": {
-    "cairn": {
+    "roteiro": {
       "command": "roteiro-agent",
-      "args": ["--server-url", "http://localhost:8080", "--api-key", "cairn_abc123"]
+      "args": ["--server-url", "http://localhost:8080", "--api-key", "roteiro_abc123"]
     }
   }
 }
@@ -71,9 +71,9 @@ Add to `.mcp.json`:
 ```json
 {
   "mcpServers": {
-    "cairn": {
+    "roteiro": {
       "command": "roteiro-agent",
-      "args": ["--server-url", "http://localhost:8080", "--api-key", "cairn_abc123"]
+      "args": ["--server-url", "http://localhost:8080", "--api-key", "roteiro_abc123"]
     }
   }
 }
@@ -105,6 +105,7 @@ Add to `.mcp.json`:
 | `compute_route_matrix` | Origin-destination time/distance matrix |
 | `compute_service_area` | Distance-based service area polygons |
 | `list_operations` | Available geoprocessing operations |
+| `list_analysis_operations` | Available advanced analysis operations |
 | `browse_catalog` | Browse the built-in data catalog |
 | `browse_catalog_enhanced` | Browse enhanced catalog with filters |
 | `get_catalog_entry` | Get enhanced catalog entry by ID |

SKILL.md

@@ -43,28 +43,17 @@ Queries must be SELECT-only (read-only).
 
 ## Geoprocessing Operations
 
-Use `run_process` for single operations or `run_pipeline` for chains. Available operations include:
-
-| Operation | Description | Key Parameters |
-|-----------|-------------|----------------|
-| `buffer` | Create buffer around features | `distance` (meters) |
-| `clip` | Clip features by a mask | `clip_dataset` |
-| `simplify` | Reduce geometry complexity | `tolerance` |
-| `reproject` | Change coordinate system | `target_crs` (e.g. "EPSG:4326") |
-| `centroid` | Calculate centroids | — |
-| `convex_hull` | Convex hull of features | — |
-| `intersection` | Intersect two datasets | `overlay_dataset` |
-| `union` | Union two datasets | `overlay_dataset` |
-| `difference` | Subtract one dataset from another | `overlay_dataset` |
-| `sjoin` | Spatial join | `join_dataset`, `predicate` |
-| `dissolve` | Merge features by attribute | `by` (field name) |
-| `voronoi` | Voronoi polygons | — |
-| `spatial_stats` | Descriptive statistics | — |
-| `morans_i` | Spatial autocorrelation | `attribute` |
-| `hotspot` | Getis-Ord Gi* hotspot analysis | `attribute` |
-| `kernel_density` | Density estimation | `bandwidth`, `cell_size` |
-
-Use `list_operations` to get the full list with parameter schemas.
+Use `run_process` for single operations or `run_pipeline` for chains.
+
+Always call `list_operations` first to fetch the live server operation catalog and parameter names. The current server supports a broad set including vector ops (`buffer`, `clip`, `intersect`, `difference`, `dissolve`, `sjoin`), geometry conversion (`centroid`, `convex_hull`, `feature_to_point`, `points_to_line`), stats (`spatial_stats`, `morans_i`, `hotspot`, `kernel_density`), interpolation (`interpolate_idw`, `ordinary_kriging`), validation (`validate`, `make_valid`, `validate_topology`), and optimization (`solve_vrp`, `p_median`, `mclp`).
+
+Important parameter names for common ops:
+- `clip` uses `mask`
+- `sjoin` uses `right` and `predicate`
+- `reproject` uses `from_crs` and `to_crs`
+- `dissolve` uses `group_by`
+
+Use `list_analysis_operations` for advanced analysis catalog endpoints under `/api/analysis/operations`.
 
 ## Data Catalog & STAC
 
@@ -115,7 +104,7 @@ GROUP BY r.name ORDER BY count DESC
 {
   "steps": [
     {"operation": "buffer", "input": "schools", "params": {"distance": 1000}},
-    {"operation": "intersection", "params": {"overlay_dataset": "residential_zones"}}
+    {"operation": "intersect", "params": {"mask": "residential_zones"}}
   ]
 }
 ```