Disable MCP servers on staging and production (#5020)

## Summary
- Set `replicaCount: 0` in both production `values.yaml` and
`values.staging.yaml`
- MCP servers have already been scaled to 0 via kubectl as an immediate
measure

## Test plan
- [ ] Verify no MCP pods are running after merge: `kubectl get pods -n
everyrow-mcp` and `kubectl get pods -n everyrow-mcp-staging`

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Sourced from commit 65c67e455c6c18d3ac229281be0dabf313def5fc

Author: RafaelPo

futuresearch-mcp/deploy/chart/values.staging.yaml

@@ -6,7 +6,7 @@
 # FUTURESEARCH_API_URL is intentionally not overridden — there is no staging API.
 # The MCP server is a frontend to the production FutureSearch API in both environments.
 
-replicaCount: 2
+replicaCount: 0
 
 env:
   MCP_SERVER_URL: "https://mcp-staging.futuresearch.ai"

futuresearch-mcp/deploy/chart/values.yaml

@@ -9,7 +9,7 @@ image:
 releaseId: "latest"
 
 # OAuth state is stored in Redis. Multiple replicas are possible.
-replicaCount: 2
+replicaCount: 0
 
 service:
   port: 80