mcpwatch

← All servers

Grade B

seekrit — secrets for agents

dev.seekrit/remote-mcp · v0.1.0 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Encrypted store for API keys and database URLs your code needs. Use them without reading them.

Source: https://github.com/mileszim/seekrit

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 40 tool(s) to anyone, no credentials needed.
MediumMW1025 tool(s) can execute commands or delete data (delete_secret, delete_app, delete_group, delete_env, delete_branch). Require confirmation before the agent calls them.

What was checked

Public tools: signup, get_started, setup_local_crypto, local_tool_for, whoami, list_orgs, list_apps, list_envs, list_branches, list_groups, list_group_envs, list_env_groups, list_members, list_secrets, list_secret_versions, list_tokens, list_invites, kms_list_keys, list_lease_targets, list_leases, audit, billing, create_app, create_group, compose_group, uncompose_group, invite_member, rename_app, rename_group, restore_secret

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/dev-seekrit-remote-mcp-d47f8df7.svg)](https://www.mcpwatch.io/s/dev-seekrit-remote-mcp-d47f8df7)