MCP Operation Risk
io.github.dnsreicht/mcp-operation-riskVersion 0.1.0Operation-level risk guidance for consolidated MCP tools, including schema drift and retry signals.
Status
Responds231 msAnswered our handshake without sign-in.- Last checked
- Nov 14, 2026, 14:49 UTC
- Latency
- 231 ms
- Remotes responding
- 1 of 1
- Sign-in
- No sign-in
- Hosting
- EU hosting detected (detected, not a legal statement)
- Registry data as of
- Nov 14, 2026, 22:14 UTC
Data from the official MCP Registry, checked by run.zero. How we check
Connect
Streamable HTTP
https://87-106-119-237.sslip.io/mcp-operation-risk/mcpResponds231 msNo sign-in
Claude Code
claude mcp add --transport http mcp-operation-risk https://87-106-119-237.sslip.io/mcp-operation-risk/mcpClaude Desktop and claude.ai
Settings > Connectors > Add custom connector
Name: mcp-operation-risk
Remote MCP server URL: https://87-106-119-237.sslip.io/mcp-operation-risk/mcpCursor
{
"mcpServers": {
"mcp-operation-risk": {
"url": "https://87-106-119-237.sslip.io/mcp-operation-risk/mcp"
}
}
}VS Code
code --add-mcp '{"name":"mcp-operation-risk","type":"http","url":"https://87-106-119-237.sslip.io/mcp-operation-risk/mcp"}'Built your own server? run.zero hosts MCP servers on European infrastructure.
Tools
2 tools
Read-only | Idempotent | Open world | ||
|---|---|---|---|---|
describe_operation_risk_serviceCheck whether the actual operation inside an MCP tool call is safe before execution. Use this when one MCP tool exposes multiple operations with different side effects, so whole-tool permissions are too coarse. Provide the native MCP server identity, the tool's tools/list metadata and the intended arguments. For supported consolidated tools, distinguish read, create/add, update/mutate and delete/destructive operations. Return ALLOW, DENY, or REQUIRE_APPROVAL. Unknown, unsupported, ambiguous, or schema-changed calls fail closed with REQUIRE_APPROVAL. The evaluator never executes the source operation. | No | Yes | Yes | No |
evaluate_operation_riskCheck whether the actual operation inside an MCP tool call is safe before execution. Use this when one MCP tool exposes multiple operations with different side effects, so whole-tool permissions are too coarse. Provide the native MCP server identity, the tool's tools/list metadata and the intended arguments. For supported consolidated tools, distinguish read, create/add, update/mutate and delete/destructive operations. Return ALLOW, DENY, or REQUIRE_APPROVAL. Unknown, unsupported, ambiguous, or schema-changed calls fail closed with REQUIRE_APPROVAL. The evaluator never executes the source operation. | No | Yes | Yes | No |
Details
- Registry status
- Active
- Published
- Oct 3, 2026
- Updated
- Oct 3, 2026
- Repository
- Not given
- Categories
- Uncategorized
- GDPR
- Not declared