Skip to main content
Glama

teleport_pack

Read-onlyIdempotent

Encrypt selected secrets into a single AES-256-GCM bundle for safe transfer between machines. Choose passphrase or recipient public keys to control who can decrypt.

Instructions

[teleport] Encrypt one or more secrets into a single AES-256-GCM bundle string that can be safely transferred between machines. Use to hand off a curated set of credentials to another developer or environment; prefer export_secrets for plaintext .env output (single machine, trusted) and tunnel_create for ephemeral one-shot delivery on the same machine. Two modes, exactly one required: passphrase (v1, symmetric — receiver needs the same string) or recipients (v2, public-key — each receiver's qring1... string from qring teleport identity; no shared secret, only the listed identities can open it). Reads each secret value (records 'export' audit events) and produces a base64-encoded ciphertext. Returns the bundle string directly. Errors with 'No secrets to pack' if the filter matched zero secrets.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keysNoWhitelist of exact key names to include. Omit to pack every secret in the requested scope.
orgIdNoOrganization identifier for org-scoped secrets. Required only when scope='org'. Example: 'acme-corp'.
scopeNoWhere the secret lives. 'global' = user keyring (default if omitted on reads), 'project' = scoped to projectPath, 'team' = team-shared (needs teamId), 'org' = org-shared (needs orgId).
teamIdNoTeam identifier for team-scoped secrets. Required only when scope='team'. Example: 'acme-platform'.
passphraseNoSymmetric passphrase used to derive the AES-256-GCM key (v1 bundle). The receiver must supply the same string to `teleport_unpack`. Pick something high-entropy and share it out-of-band. Mutually exclusive with `recipients`.
recipientsNoRecipient public keys (`qring1...` strings, one per teammate) for a v2 recipient pack. The bundle can only be opened by the matching private keys, which each receiver created with `qring teleport keygen`. Mutually exclusive with `passphrase`.
projectPathNoAbsolute path to the project root for project-scoped secrets and policy resolution. Defaults to the MCP server's current working directory when omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.18.0
    • changedInput schema / properties / passphrase / description
      Previous value: -"Symmetric passphrase used to derive the AES-256-GCM key. The receiver must supply the same string to `teleport_unpack`. Pick something high-entropy and share it out-of-band."New value: +"Symmetric passphrase used to derive the AES-256-GCM key (v1 bundle). The receiver must supply the same string to `teleport_unpack`. Pick something high-entropy and share it out-of-band. Mutually exclusive with `recipients`."
    • addedInput schema / properties / recipients
      Added value: +{
      +  "description": "Recipient public keys (`qring1...` strings, one per teammate) for a v2 recipient pack. The bundle can only be opened by the matching private keys, which each receiver created with `qring teleport keygen`. Mutually exclusive with `passphrase`.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "passphrase"
      -]
  2. Changed6 schema fields changedv0.11.7
    • changedInput schema / properties / keys / description
      Previous value: -"Specific keys to pack (all if omitted)"New value: +"Whitelist of exact key names to include. Omit to pack every secret in the requested scope."
    • changedInput schema / properties / orgId / description
      Previous value: -"Org identifier for org-scoped secrets"New value: +"Organization identifier for org-scoped secrets. Required only when scope='org'. Example: 'acme-corp'."
    • changedInput schema / properties / passphrase / description
      Previous value: -"Encryption passphrase"New value: +"Symmetric passphrase used to derive the AES-256-GCM key. The receiver must supply the same string to `teleport_unpack`. Pick something high-entropy and share it out-of-band."
    • changedInput schema / properties / projectPath / description
      Previous value: -"Project root path for project-scoped secrets"New value: +"Absolute path to the project root for project-scoped secrets and policy resolution. Defaults to the MCP server's current working directory when omitted."
    • changedInput schema / properties / scope / description
      Previous value: -"Scope: global, project, team, or org"New value: +"Where the secret lives. 'global' = user keyring (default if omitted on reads), 'project' = scoped to projectPath, 'team' = team-shared (needs teamId), 'org' = org-shared (needs orgId)."
    • changedInput schema / properties / teamId / description
      Previous value: -"Team identifier for team-scoped secrets"New value: +"Team identifier for team-scoped secrets. Required only when scope='team'. Example: 'acme-platform'."
  3. Changed4 schema fields changedv0.11.5
    • addedInput schema / properties / orgId
      Added value: +{
      +  "description": "Org identifier for org-scoped secrets",
      +  "type": "string"
      +}
    • changedInput schema / properties / scope / description
      Previous value: -"Scope: global or project"New value: +"Scope: global, project, team, or org"
    • changedInput schema / properties / scope / enum
      Previous value: -[
      -  "global",
      -  "project"
      -]New value: +[
      +  "global",
      +  "project",
      +  "team",
      +  "org"
      +]
    • addedInput schema / properties / teamId
      Added value: +{
      +  "description": "Team identifier for team-scoped secrets",
      +  "type": "string"
      +}
  4. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond annotations by disclosing that it reads each secret value, records 'export' audit events, produces base64-encoded ciphertext, returns the bundle string directly, and errors with 'No secrets to pack' on zero matches. This gives the agent a complete behavioral model without any dependence on annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and then methodically covers usage scenarios, modes, side effects, and return/error behavior. While it's on the longer side, every sentence earns its place and the structure is logical, so it doesn't feel bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters, two mutually exclusive modes, no output schema, and spin-off effects like audit events, the description covers all critical contexts: how to select the tool, the meaning of each mode, the return value, and the error condition. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and each parameter has detailed descriptions in the schema (e.g., mutual exclusivity, defaults, examples). The description text reinforces the two modes but doesn't add semantic meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Encrypt one or more secrets into a single AES-256-GCM bundle string') and resource, and immediately differentiates itself from siblings by naming `export_secrets` and `tunnel_create` as alternatives. It also explains the two modes, so an agent can tell exactly what the tool does and how it differs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use the tool ('hand off a curated set of credentials to another developer or environment') and provides concrete alternatives with their conditions ('prefer export_secrets for plaintext .env output... tunnel_create for ephemeral one-shot delivery'). It also clarifies the choice between passphrase and recipients modes, making the routing decision unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.