git_push_creds

SERVERYaver SOURCEyaver-cli

Medium RISK CLASS

Category Write

Parameters 100 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-kivanccakmak-yaver/git-push-creds.md

WHAT IT DOES

What git_push_creds does on Yaver

AI agents use git_push_creds to create or update resources in Yaver, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.

Parameter	Type	Required	Description
`all`	boolean	—	Fan out to every owned online peer (excludes this machine)
`notes`	string	—
`provider`	string	—	Which provider(s) to push (default all)
`device_id`	string	—	Single owned remote device ID or alias
`device_ids`	array	—	Multiple owned remote device IDs/aliases
`apply_clone`	boolean	—	Write clone/pull credentials on each target (default true)
`gitlab_host`	string	—	Defaults to gitlab.com
`github_token`	string	—	Override auto-detection (omit to detect locally)
`gitlab_token`	string	—	Override auto-detection (omit to detect locally)
`apply_ci_token`	boolean	—	Write CI/deploy vault token on each target (default true)

Parameters from the server's own tool schema.

RISK

Why git_push_creds is rated Medium

The tool creates or propagates credentials/secrets to remote machines, which is a reversible configuration modification. While it handles sensitive tokens, the core action is writing/installing credentials to remote systems rather than executing arbitrary code or destructively deleting data.

From the tool's definition Tool description states it 'Forward[s] locally detected GitHub/GitLab tokens... to one or more owned remote Yaver machines' via an endpoint. This modifies remote machine credentials/configuration state.

Risk signalsHigh parameter count (10 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs git_push_creds safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For git_push_creds, this is the rule to start with:

git_push_creds Rate-limited

git_push_creds stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "git_push_creds": {
      "limits": [
        {
          "counter": "git_push_creds_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every git_push_creds call is checked against it from then on.

FAQ

Questions about git_push_creds

What does the git_push_creds tool do? +

Forward locally detected GitHub/GitLab tokens (gh CLI, env vars, git credential helper, vault) to one or more owned remote Yaver machines via the same /machine/onboarding/apply endpoint as the dashboard. Lets a fresh remote box (Hetzner runner, managed cloud, …) get clone-pull creds plus CI/deploy vault tokens without re-pasting a PAT. Self is always excluded — use machine_onboarding_apply or vault tools for the local machine. Tokens never reach Convex. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does git_push_creds accept? +

git_push_creds accepts 10 parameters: all, notes, provider, device_id, device_ids, apply_clone, gitlab_host, github_token, gitlab_token, apply_ci_token. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on git_push_creds? +

Register the Yaver MCP server in PolicyLayer and add a rule for git_push_creds: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.

What risk level is git_push_creds? +

git_push_creds is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit git_push_creds? +

Yes. Add a rate_limit block to the git_push_creds rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block git_push_creds completely? +

Set action: deny in the PolicyLayer policy for git_push_creds. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides git_push_creds? +

git_push_creds is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Yaver, and thousands of servers like it.

This server

All 645 Yaver tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →