# MCP Operation Risk

> Operation-level risk guidance for consolidated MCP tools, including schema drift and retry signals.

- name: io.github.dnsreicht/mcp-operation-risk
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.dnsreicht%2Fmcp-operation-risk
- tools: https://api.protogrid.dev/v1/servers/io.github.dnsreicht%2Fmcp-operation-risk/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "mcp-operation-risk": {
      "type": "http",
      "url": "https://87-106-119-237.sslip.io/mcp-operation-risk/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 45
- drivers: +website +reachable +uptime-100% +updated-17d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 2 of 2 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,160 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 6 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 1,160 tokens to load them all
- tool set hash: bdea22463be1c37d2841019f5a1ce147
- tools last changed: 2026-10-05T02:01:57.926Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.dnsreicht/mcp-operation-risk.svg)](https://protogrid.dev/servers/io.github.dnsreicht/mcp-operation-risk)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-05 `evaluate_operation_risk` changed (title, description)
  - before: Check whether an intended MCP tool call is safe before execution. Using the source server identity, tool metadata, input schema, and planned arguments, return an operation-level ALLOW, DENY, or REQUIRE_APPROVAL decision. For supported consolidated tools, distinguish read, additive, mutating, and destructive operations, including supported create, update, and delete commands. Unknown, unsupported, or schema-changed calls require approval. Use when whole-tool permissions are too coarse; the evaluator never executes the source call.
  - after: Check 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.
- 2026-10-05 `describe_operation_risk_service` changed (description)
  - before: Check whether an intended MCP tool call is safe before execution. Using the source server identity, tool metadata, input schema, and planned arguments, return an operation-level ALLOW, DENY, or REQUIRE_APPROVAL decision. For supported consolidated tools, distinguish read, additive, mutating, and destructive operations, including supported create, update, and delete commands. Unknown, unsupported, or schema-changed calls require approval. Use when whole-tool permissions are too coarse; the evaluator never executes the source call.
  - after: Check 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.
- 2026-10-04 `evaluate_operation_risk` changed (description, inputSchema) **meaning changed**
  - before: Evaluate the operation-level risk of an intended MCP tool call before execution. Returns ALLOW, DENY, or REQUIRE_APPROVAL.
  - after: Check whether an intended MCP tool call is safe before execution. Using the source server identity, tool metadata, input schema, and planned arguments, return an operation-level ALLOW, DENY, or REQUIRE_APPROVAL decision. For supported consolidated tools, distinguish read, additive, mutating, and destructive operations, including supported create, update, and delete commands. Unknown, unsupported, or schema-changed calls require approval. Use when whole-tool permissions are too coarse; the evaluator never executes the source call.
- 2026-10-04 `describe_operation_risk_service` changed (description) **meaning changed**
  - before: Analyzes operation-level risk inside consolidated MCP tools. Designed for MCP tools where one tool exposes multiple operations through command/action/method arguments and those operations require different policy outcomes. Returns evidence-backed ALLOW, DENY, or REQUIRE_APPROVAL, schema-drift status, retry semantics, and deterministic operation effect identity. Paid evaluations use x402.
  - after: Check whether an intended MCP tool call is safe before execution. Using the source server identity, tool metadata, input schema, and planned arguments, return an operation-level ALLOW, DENY, or REQUIRE_APPROVAL decision. For supported consolidated tools, distinguish read, additive, mutating, and destructive operations, including supported create, update, and delete commands. Unknown, unsupported, or schema-changed calls require approval. Use when whole-tool permissions are too coarse; the evaluator never executes the source call.
- 2026-10-04 `evaluate_operation_risk` changed (inputSchema)
- 2026-10-04 `evaluate_operation_risk` added
  - Evaluate the operation-level risk of an intended MCP tool call before execution. Returns ALLOW, DENY, or REQUIRE_APPROVAL.

Full history: https://api.protogrid.dev/v1/servers/io.github.dnsreicht%2Fmcp-operation-risk/changes

## Remotes

- https://87-106-119-237.sslip.io/mcp-operation-risk/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (2)

- `describe_operation_risk_service`: Check 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.
- `evaluate_operation_risk`: Check 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.