# seekrit — secrets for agents (remote · mcp.seekrit.dev)

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

- Trust score: 56/100 (low)
- Change this week: +38
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

> **Recent critical change**: Authorization (2026-07-30). See the changelog below before you install this server.

## Components

- remote · `mcp.seekrit.dev`: 56/100 (this document), [markdown](https://verifymcp.io/servers/dev-seekrit-remote-mcp/mcp.md), [page](https://verifymcp.io/servers/dev-seekrit-remote-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.seekrit.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete_secret).
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 2446 tokens (~61/item across 40 items; 40 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 69/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 8% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http dev-seekrit-remote-mcp https://mcp.seekrit.dev/mcp
```

### Codex

```toml
[mcp_servers.dev-seekrit-remote-mcp]
url = "https://mcp.seekrit.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-seekrit-remote-mcp": {
      "type": "remote",
      "url": "https://mcp.seekrit.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-seekrit-remote-mcp --url https://mcp.seekrit.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-seekrit-remote-mcp:
    url: "https://mcp.seekrit.dev/mcp"
```

### Other

```json
{
  "mcpServers": {
    "dev-seekrit-remote-mcp": {
      "type": "http",
      "url": "https://mcp.seekrit.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 55, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 54, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 56, +38)

- [critical] Authorization: Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (delete_secret).
- [security improvement] Transport: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 8

### 2026-07-27 (score 18, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 18)

First indexed and scored.

## MCP tools (40)

### `signup` (~200 tokens)

Create a seekrit workspace and your own machine credential — one call, no human, no browser. Binds the credential to this session, so every other tool works on your next call with no config change and no reconnect. Save the returned clientId + clientSecret: the secret is shown once and is how you reconnect later. Call this if a tool says you have no credential.

Input parameters:

- `clientName` (string): Optional label for this machine credential (defaults to <slug>-agent).
- `orgName` (string, required): The real project, product, or company this workspace is for (e.g. "Acme Storefront") — NOT a placeholder like "test" or "agent". A human will later claim the org by this name.
- `orgSlug` (string, required): URL-safe identifier derived from the project, lowercase letters/numbers/hyphens (e.g. "acme-storefront"). Throwaway slugs make the org unmanageable.

### `get_started` (~32 tokens)

The recommended first-project recipe: what to provision here vs. encrypt locally, end to end. Call this before provisioning.

### `setup_local_crypto` (~66 tokens)

How to run the local crypto plane (the `@seekrit/mcp` npm server, the CLI, or seekrit-run) so you can set and use secret values — with a copy-paste .mcp.json. Call this the moment you need a secret's value.

### `local_tool_for` (~67 tokens)

Given a crypto-plane operation this hosted server can't do (e.g. set_secret, create_env, run_command), return exactly how to do it locally. Use when a tool you expected is missing here.

Input parameters:

- `operation` (string, required): the operation you wanted, e.g. set_secret

### `whoami` (~24 tokens)

Show the authenticated machine client and the org it can access. Call this first.

### `list_orgs` (~16 tokens)

List organizations the caller can access.

### `list_apps` (~21 tokens)

List applications in an organization.

Input parameters:

- `org` (string)

### `list_envs` (~38 tokens)

List environments of an application (names + slugs only, never values).

Input parameters:

- `app` (string, required)
- `org` (string)

### `list_branches` (~62 tokens)

List ephemeral branch configs (per-PR / preview environments) in an application, or of one environment. Names, parents, and expiry only — never values.

Input parameters:

- `app` (string, required)
- `env` (string)
- `org` (string)

### `list_groups` (~28 tokens)

List shared groups (reusable secret bags) in an organization.

Input parameters:

- `org` (string)

### `list_group_envs` (~35 tokens)

List a group's environments (per-slug value sets).

Input parameters:

- `group` (string, required)
- `org` (string)

### `list_env_groups` (~43 tokens)

List the groups composed into an application environment (precedence order).

Input parameters:

- `app` (string, required)
- `env` (string, required)
- `org` (string)

### `list_members` (~29 tokens)

List organization members and their public keys (used when granting access locally).

Input parameters:

- `org` (string)

### `list_secrets` (~58 tokens)

List secret names + versions in an environment. NEVER returns values — reading a value happens on the local crypto plane (see setup_local_crypto).

Input parameters:

- `app` (string, required)
- `env` (string, required)
- `org` (string)

### `list_secret_versions` (~83 tokens)

List a secret's version history: who wrote each version, when, and which ones were restores. Metadata only — never values. Pair with restore_secret to undo a bad write.

Input parameters:

- `app` (string, required)
- `env` (string, required)
- `limit` (integer): default 20
- `name` (string, required)
- `org` (string)

### `list_tokens` (~29 tokens)

List an organization's service tokens (metadata only — never the token strings).

Input parameters:

- `org` (string)

### `list_invites` (~24 tokens)

List pending invitations to join the organization.

Input parameters:

- `org` (string)

### `kms_list_keys` (~37 tokens)

List managed KMS keys the caller can see (metadata only — key material is fetched + used locally).

Input parameters:

- `org` (string)

### `list_lease_targets` (~32 tokens)

List registered temporary-access provisioning targets (Postgres, MySQL, …).

Input parameters:

- `org` (string)

### `list_leases` (~28 tokens)

List temporary-access leases (the ledger — never secret material).

Input parameters:

- `org` (string)

### `audit` (~47 tokens)

Read the organization's audit trail (most recent first).

Input parameters:

- `action` (string): filter by action, e.g. secret.updated
- `limit` (integer)
- `org` (string)

### `billing` (~47 tokens)

Show the org's plan, effective entitlements, current usage, and which upgrade actions are available. Read this if a create action was refused with a plan limit.

Input parameters:

- `org` (string)

### `create_app` (~58 tokens)

Create an application in an organization. Keyless — then create its environments on the local crypto plane (create_env mints the data key locally).

Input parameters:

- `name` (string, required)
- `org` (string)
- `slug` (string, required)

### `create_group` (~46 tokens)

Create a shared group (reusable secret bag) in an organization. Keyless.

Input parameters:

- `name` (string, required)
- `org` (string)
- `slug` (string, required)

### `compose_group` (~61 tokens)

Compose a group into an application environment (higher position wins on name clashes). Keyless.

Input parameters:

- `app` (string, required)
- `env` (string, required)
- `group` (string, required)
- `org` (string)
- `position` (integer)

### `uncompose_group` (~49 tokens)

Remove a composed group from an application environment. Keyless.

Input parameters:

- `app` (string, required)
- `env` (string, required)
- `group` (string, required)
- `org` (string)

### `invite_member` (~53 tokens)

Invite someone to the organization by email (admin only). They join at the given role once they sign in.

Input parameters:

- `email` (string, required)
- `org` (string)
- `role` (string): default member

### `rename_app` (~43 tokens)

Rename an application's display name (the slug is immutable). Keyless.

Input parameters:

- `app` (string, required)
- `name` (string, required)
- `org` (string)

### `rename_group` (~43 tokens)

Rename a group's display name (the slug is immutable). Keyless.

Input parameters:

- `group` (string, required)
- `name` (string, required)
- `org` (string)

### `restore_secret` (~94 tokens)

Roll a secret back to an earlier version (see list_secret_versions). The stored ciphertext is replayed as a NEW version — history is append-only, nothing is overwritten. Keyless: no decryption happens, so this works here on the metadata plane.

Input parameters:

- `app` (string, required)
- `env` (string, required)
- `name` (string, required)
- `org` (string)
- `version` (integer, required)

### `delete_secret` (~62 tokens)

Delete a secret from an environment. Removes ciphertext — no key needed. Irreversible except by re-setting it (locally).

Input parameters:

- `app` (string, required)
- `env` (string, required)
- `name` (string, required)
- `org` (string)

### `revoke_token` (~55 tokens)

Revoke a service token by id. Future DEK fetches stop immediately. Rotate the environment (locally) if the holder may have cached the key.

Input parameters:

- `org` (string)
- `tokenId` (string, required)

### `revoke_invite` (~31 tokens)

Revoke a pending organization invitation.

Input parameters:

- `inviteId` (string, required)
- `org` (string)

### `revoke_lease` (~37 tokens)

Revoke a temporary-access lease now (drops the credential immediately).

Input parameters:

- `leaseId` (string, required)
- `org` (string)

### `kms_disable_key` (~50 tokens)

Disable a managed KMS key (blocks new operations; existing ciphertexts stay decryptable locally by grantees). Keyless.

Input parameters:

- `keyId` (string, required)
- `org` (string)

### `kms_revoke_grant` (~72 tokens)

Revoke a principal's grant on a managed KMS key (all versions). Keyless — the caller needs no key material to remove a grant.

Input parameters:

- `keyId` (string, required)
- `org` (string)
- `principalId` (string, required)
- `principalType` (string, required)

### `delete_app` (~46 tokens)

Delete an application and all its environments/secrets. Removes ciphertext — keyless — but irreversible. Confirm intent before calling.

Input parameters:

- `app` (string, required)
- `org` (string)

### `delete_group` (~45 tokens)

Delete a group and its environments/secrets. Removes ciphertext — keyless — but irreversible. Confirm intent before calling.

Input parameters:

- `group` (string, required)
- `org` (string)

### `delete_env` (~51 tokens)

Delete an application environment and its secrets. Removes ciphertext — keyless — but irreversible. Confirm intent before calling.

Input parameters:

- `app` (string, required)
- `env` (string, required)
- `org` (string)

### `delete_branch` (~78 tokens)

Tear down an ephemeral branch config and every value it overrode. Keyless (it removes ciphertext, never reads it), and the parent environment is untouched. Creating a branch mints a data key, so that stays on the local crypto plane.

Input parameters:

- `app` (string, required)
- `branch` (string, required)
- `org` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-seekrit-remote-mcp/mcp#diagnostics

## Score history

- 2026-08-03: 56
- 2026-08-02: 55
- 2026-08-01: 55
- 2026-07-31: 54
- 2026-07-30: 56
- 2026-07-29: 18
- 2026-07-28: 18
- 2026-07-27: 18
- 2026-07-26: 18

## Links

- Remote endpoint: https://mcp.seekrit.dev/mcp
- Repository: https://github.com/mileszim/seekrit
- Changelog RSS feed: https://verifymcp.io/servers/dev-seekrit-remote-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-seekrit-remote-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/dev-seekrit-remote-mcp/mcp