Skip to main content
Glama
wundervault

wundervault

Official

vault_git

Run git push, pull, fetch, clone, or ls-remote over SSH with a vaulted key kept in the broker; only approved servers can connect.

Instructions

Run git push, pull, fetch, clone or ls-remote over SSH with a vaulted SSH key that never leaves the broker. Every address git would connect to (including a separate push address and any rewrite in git config) must be a server approved for the entry, or nothing connects; for a key saved without servers, the first use of a new server asks the owner. Only SSH remotes; no submodules, no hooks during the run. Linux and macOS only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "entry_id": "<entry_id>",
      "purpose": "<purpose>",
      "subcommand": "<subcommand>",
      "repo_dir": "<repo_dir>"
    },
    "name": "vault_git"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoclone only: the SSH address, e.g. git@github.com:owner/repo.git.
flagsNoAllowed: push --force-with-lease --tags --set-upstream --dry-run --delete --follow-tags; pull --ff-only --rebase --no-rebase; fetch --tags --prune --dry-run --depth=N; clone --depth=N --branch=NAME --single-branch --no-checkout; ls-remote --heads --tags.
remoteNoNamed remote, e.g. origin. Required except for clone.
purposeYesWhy (activity log).
entry_idYesVault entry holding the SSH key.
refspecsNopush/pull/fetch: branches or refspecs, e.g. ["main"].
repo_dirYesThe local repository (for clone: the folder to clone into).
subcommandYes
target_dirNoclone only: folder name to create inside repo_dir.
timeout_secondsNoDefault 120, at most 870.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.4.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations at all, the description carries the full behavioral burden and does substantial work: it discloses the server-approval gate covering every address git would connect to (including push addresses and git config rewrites), the first-use owner prompt for keys without servers, and that the key never leaves the broker. It omits failure behavior and what the call returns, which matters because push with --force-with-lease and --delete are state-changing operations on the remote.

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

Conciseness5/5

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

A single tight paragraph with the capability stated first, then the security model, then the hard limits. Every clause constrains behavior an agent would otherwise have to guess at, and nothing is repeated from the schema.

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

Completeness4/5

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

For a 10-parameter tool with no annotations and no output schema, the description covers the security model, permitted remotes, and platform scope well. The remaining gap is the absence of any statement about return values or error behavior, which the missing output schema leaves entirely undocumented.

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 90%, so the schema already documents entry_id, url, remote, refspecs, flags, repo_dir, target_dir, and timeout_seconds in detail. The description adds no per-parameter semantics beyond reiterating that all connect addresses must be approved servers, which is behavioral rather than parameter guidance. Baseline 3 applies.

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 names the exact operations (git push, pull, fetch, clone, ls-remote) and the transport/credential mechanism (SSH with a vaulted key held by the broker). That is enough for an agent to separate this from vault_ssh_exec, which runs arbitrary commands rather than git subcommands.

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

Usage Guidelines4/5

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

It states clear usage boundaries: SSH remotes only, no submodules, no hooks during the run, Linux and macOS only. It does not explicitly say when to prefer this over vault_ssh_exec, so the routing guidance is implied by the platform and git-specific constraints rather than spelled out.

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