runpod-runpod-mcp-ts
mcp1.1.0By runpod | 73 findings | Scanned 6/22/2026 | tooltrust-scanner/v0.3.19 | 55
Risk Summary
Safe With Normal ControlsMissing Description is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (73)
input schema exposes 11 properties (threshold: 10)
create-podcreate-templateFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
get-endpointdelete-endpointcreate-templateFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool 'list-pods' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
list-podsTool 'get-pod' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
get-podTool 'create-pod' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
create-podTool 'update-pod' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
update-podTool 'start-pod' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
start-podTool 'stop-pod' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
stop-podTool 'delete-pod' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
delete-podTool 'list-endpoints' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
list-endpointsTool 'get-endpoint' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
get-endpointTool 'create-endpoint' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
create-endpointTool 'update-endpoint' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
update-endpointTool 'delete-endpoint' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
delete-endpointTool 'list-templates' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
list-templatesTool 'get-template' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
get-templateTool 'create-template' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
create-templateTool 'update-template' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
update-templateTool 'delete-template' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
delete-templateTool 'list-network-volumes' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
list-network-volumesTool 'get-network-volume' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
get-network-volumeTool 'create-network-volume' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
create-network-volumeTool 'update-network-volume' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
update-network-volumeTool 'delete-network-volume' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
delete-network-volumeTool 'list-container-registry-auths' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
list-container-registry-authsTool 'get-container-registry-auth' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
get-container-registry-authTool 'create-container-registry-auth' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
create-container-registry-authTool 'delete-container-registry-auth' has no description - agents cannot reason about its purpose, and static analysis coverage is limited
delete-container-registry-authFix: Review and remediate the identified issue.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
list-podsget-podcreate-podupdate-podstart-podstop-poddelete-podlist-endpointsget-endpointcreate-endpointupdate-endpointdelete-endpointlist-templatesget-templatecreate-templateupdate-templatedelete-templatelist-network-volumesget-network-volumecreate-network-volumeupdate-network-volumedelete-network-volumelist-container-registry-authsget-container-registry-authcreate-container-registry-authdelete-container-registry-authFix: Review and remediate the identified issue.
declared capabilities: filesystem access, environment variables
create-podupdate-podupdate-templatedeclared capabilities: filesystem access
delete-podcreate-endpointdelete-templatecreate-network-volumeupdate-network-volumedelete-network-volumecreate-container-registry-authdelete-container-registry-authdeclared capabilities: network access
get-endpointdeclared capabilities: network access, filesystem access
update-endpointdelete-endpointdeclared capabilities: code/command execution, filesystem access, environment variables
create-templateFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
create-container-registry-auth:input parameter "password" accepts a credential (informational; not evidence of insecure handling)
Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y runpod-runpod-mcp-ts"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)