Update to Render

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -2,8 +2,8 @@
 name: render-mcp
 description: >-
   Connects and configures the Render MCP server for AI coding tools—setup per
-  tool (Cursor, Claude Code, Codex), authentication, workspace selection, tool
-  catalog, and troubleshooting. Use when MCP is not configured, list_services()
+  tool (Cursor, Claude Code, Codex), authentication, workspace selection,
+  capability discovery, and troubleshooting. Use when MCP is not configured, list_services()
   fails, the user asks about Render MCP setup, or an action skill needs MCP
   but it's not connected yet.
   Trigger terms: MCP, Render MCP, list_services, MCP setup, MCP server,
@@ -18,10 +18,12 @@
 
 # Render MCP Server
 
-The Render MCP server lets AI coding tools manage Render services, databases, deploys, logs, and metrics directly. This skill covers **setup**, **authentication**, **workspace selection**, the **tool catalog**, and **troubleshooting**.
+The Render MCP server lets AI coding tools manage Render resources directly. This skill covers **setup**, **authentication**, **workspace selection**, **capability discovery**, and **troubleshooting**.
 
 Action skills (render-deploy, render-debug, render-monitor) use MCP tools for their workflows. If MCP is not connected, set it up using this skill first.
 
+Before configuring, troubleshooting, or using Render MCP, read `references/render-access.md` for the current server, authentication, workspace, capability-discovery, and fallback workflow.
+
 ## When to Use
 
 - `list_services()` fails or MCP tools are unavailable
@@ -30,29 +32,15 @@
 - Switching workspaces or troubleshooting auth errors
 - Discovering which MCP tools exist and what they do
 
-## Connection Details
-
-| Property | Value |
-|----------|-------|
-| URL | `https://mcp.render.com/mcp` |
-| Transport | HTTP (streamable) |
-| Auth | OAuth when installed via the Render plugin (pre-registered client id); bearer token (API key) for manual setup |
-| API key page | `https://dashboard.render.com/u/*/settings#api-keys` (manual setup) |
-| Docs | `https://render.com/docs/mcp-server` |
-
-## Setup by Tool
-
-### Render plugin (recommended)
+## Current Setup and Capabilities
 
-The Render plugin for Cursor, Codex, and Claude Code bundles this MCP server with a pre-registered OAuth client id, so no API key is needed. After installing or updating the plugin, reload the tool (restart Cursor or Claude Code, or start a new Codex thread) so it loads the plugin-provided MCP server, then complete the Render OAuth prompt the first time MCP tools are used. Verify with `list_services()`.
+Follow `references/render-access.md` to fetch the current MCP documentation, configure the client, verify read-only access, select the intended workspace, and inspect the tools actually available. Do not rely on a memorized tool catalog.
 
-The manual, API-key setups below are for tools without the plugin or for custom MCP configurations.
+If the user has not identified their AI tool, ask which tool they use before giving client-specific setup instructions. Prefer the official Render plugin or connector and its browser-based OAuth flow when available. For a manual API-key setup, create a key at `https://dashboard.render.com/u/settings#api-keys` and use the hosted endpoint `https://mcp.render.com/mcp`.
 
-### Cursor
+### Manual client setup
 
-1. Get an API key from the [Render Dashboard](https://dashboard.render.com/u/*/settings#api-keys)
-
-2. Add to `~/.cursor/mcp.json`:
+For Cursor, add this configuration to `~/.cursor/mcp.json`, restart Cursor, and verify the connection with `list_services()`:
 
 ```json
 {
@@ -67,142 +55,19 @@
 }
 ```
 
-3. Restart Cursor, then verify with `list_services()`
-
-### Claude Code
-
-1. Get an API key from the [Render Dashboard](https://dashboard.render.com/u/*/settings#api-keys)
-
-2. Add the MCP server:
+For Claude Code, add the server with:
 
 ```bash
 claude mcp add --transport http render https://mcp.render.com/mcp --header "Authorization: Bearer <YOUR_API_KEY>"
 ```
 
-3. Restart Claude Code, then verify with `list_services()`
-
-### Codex
-
-1. Get an API key from the [Render Dashboard](https://dashboard.render.com/u/*/settings#api-keys)
-
-2. Set the key in your shell:
-
-```bash
-export RENDER_API_KEY="<YOUR_API_KEY>"
-```
-
-3. Add the MCP server:
-
-```bash
-codex mcp add render --url https://mcp.render.com/mcp --bearer-token-env-var RENDER_API_KEY
-```
-
-4. Restart Codex, then verify with `list_services()`
-
-### Other Tools
-
-For tools not listed above, use the generic HTTP MCP configuration:
-
-- **URL:** `https://mcp.render.com/mcp`
-- **Auth header:** `Authorization: Bearer <YOUR_API_KEY>`
-- **Transport:** HTTP (streamable HTTP, not SSE)
-
-See [Render MCP docs](https://render.com/docs/mcp-server) for tool-specific instructions.
-
-## Workspace Selection
-
-After MCP is connected, set the active workspace:
-
-```
-Set my Render workspace to [WORKSPACE_NAME]
-```
-
-Or programmatically:
-
-```
-get_selected_workspace()   # Check current
-list_workspaces()          # List available
-```
-
-All MCP operations run against the active workspace.
-
-## Tool Catalog
-
-### Service management
-
-| Tool | Purpose |
-|------|---------|
-| `list_services()` | List all services and datastores |
-| `get_service(serviceId)` | Get service details |
-| `create_web_service(...)` | Create a web service from Git repo |
-| `create_static_site(...)` | Create a static site from Git repo |
-| `update_service(serviceId, ...)` | Update service configuration |
-| `restart_service(serviceId)` | Restart a service |
-
-### Deploys
-
-| Tool | Purpose |
-|------|---------|
-| `list_deploys(serviceId, limit)` | List deploys for a service |
-| `trigger_deploy(serviceId)` | Trigger a new deploy |
-
-### Logs
-
-| Tool | Purpose |
-|------|---------|
-| `list_logs(resource, level, type, text, statusCode, limit)` | Query logs with filters |
-
-Key filters: `level` (error, warn, info), `type` (build, deploy), `text` (search string), `statusCode` (HTTP codes).
-
-### Metrics
+Restart Claude Code and verify with `list_services()`. To replace a stale manual configuration, run `claude mcp remove render` before adding it again.
 
-| Tool | Purpose |
-|------|---------|
-| `get_metrics(resourceId, metricTypes, ...)` | Get service or database metrics |
+For Codex, follow the current OAuth or API-key configuration fetched through `references/render-access.md`. If the configuration obtains its bearer token from `RENDER_API_KEY`, that variable must be available in the environment where Codex starts; restart Codex after changing it.
 
-Metric types: `cpu_usage`, `memory_usage`, `cpu_limit`, `memory_limit`, `http_latency`, `http_request_count`, `active_connections`.
+### Empty results and workspace selection
 
-Optional: `httpLatencyQuantile` (0.5, 0.95, 0.99), `httpPath` (filter by endpoint).
-
-### Databases
-
-| Tool | Purpose |
-|------|---------|
-| `list_postgres_instances()` | List Postgres databases |
-| `get_postgres(postgresId)` | Get database details |
-| `query_render_postgres(postgresId, sql)` | Run SQL query |
-
-### Key Value
-
-| Tool | Purpose |
-|------|---------|
-| `list_key_value()` | List Key Value instances |
-| `get_key_value(keyValueId)` | Get Key Value details |
-
-### Environment Variables
-
-| Tool | Purpose |
-|------|---------|
-| `update_environment_variables(serviceId, envVars)` | Set env vars on a service |
-
-### Workspace
-
-| Tool | Purpose |
-|------|---------|
-| `list_workspaces()` | List available workspaces |
-| `get_selected_workspace()` | Get the active workspace |
-
-## Common Mistakes
-
-| Mistake | Fix |
-|---------|-----|
-| Wrong URL (using SSE endpoint) | Use `https://mcp.render.com/mcp` (not `/sse`) |
-| Plugin installed but MCP tools unavailable | Reload the tool (restart, or start a new thread) so it loads the plugin's MCP server |
-| OAuth prompt does not appear | Reinstall or update the Render plugin, then reload the tool |
-| Expired or invalid API key | Generate a new key from Dashboard > Account Settings > API Keys |
-| Wrong workspace selected | Run `list_workspaces()` and switch to the correct one |
-| Using MCP to create image-backed services | Not supported — use Dashboard or API for prebuilt Docker images |
-| Missing `Bearer` prefix in auth header | Header must be `Authorization: Bearer <key>` |
+MCP operations run against the active workspace. If `list_services()` connects successfully but returns no services, first call `get_selected_workspace()`, then `list_workspaces()` if the wrong workspace might be selected. Also verify that the credential or `RENDER_API_KEY` belongs to an account with access to the intended workspace. Do not diagnose the server URL as the primary problem when the MCP call itself succeeds.
 
 ## Troubleshooting
 
@@ -212,6 +77,7 @@
 
 | Document | Contents |
 |----------|----------|
+| `references/render-access.md` | Current MCP and CLI access, authentication, workspace, capability-discovery, and authorization workflow |
 | `references/troubleshooting.md` | Connection errors, auth failures, tool-specific issues, timeout handling |
 
 ## Related Skills
@@ -220,3 +86,16 @@
 - **render-debug** — Debug failures using MCP logs and metrics
 - **render-monitor** — Monitor health using MCP metrics
 - **render-cli** — CLI alternative when MCP is unavailable
+
+<!-- shared:documentation-retrieval -->
+## Current documentation retrieval
+
+Whenever this skill directs you to consult current Render documentation:
+
+1. Retrieve the linked Markdown document directly with an available URL-fetching tool or HTTP client, such as `curl`. Do not substitute web-search summaries for the document.
+2. Confirm that retrieval succeeded and returned the expected document, then read its contents. Saving a file or printing its path is not sufficient.
+3. If the request fails or your tool cannot read the Markdown response, open and read the linked HTML version instead.
+4. If neither version can be retrieved, disclose that the current reference is unavailable and follow any topic-specific fallback in the skill. Use bundled guidance only for stable constraints, and do not guess at changeable platform details.
+
+When a task requires multiple references, apply this workflow to each one and distinguish the documents you verified from those that remain unavailable.
+<!-- /shared:documentation-retrieval -->