A tool-access control plugin that gives each agent a job-specific key. The key can limit permissions but cannot add new ones.

It is for enforcing least-privilege access on every tool call.

It blocks tool calls outside the permissions granted for the agent's job, including calls caused by prompt injection.

telekey — Plugin by stefans71

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add stefans71/telekey-mcp

agentmods

npx agentmods add plugins/stefans71/telekey-mcp/plugin

Clone the repo

git clone --depth 1 https://github.com/stefans71/telekey-mcp

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

telekey scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/.claude-plugin/plugin.json · 33 lines

What it actually says

{
  "name": "telekey",
  "version": "0.2.0",
  "description": "Give each agent a key scoped to one job that can only narrow, never widen. A prompt-injected agent reaches for a capability it was never given \u2014 the call is blocked before it runs. Enforced on every tool call via a PreToolUse hook.",
  "author": "stefans71",
  "license": "MIT",
  "keywords": [
    "mcp-security",
    "prompt-injection",
    "agent-security",
    "least-privilege",
    "claude-code",
    "capability",
    "delegation",
    "hooks",
    "mcp",
    "security"
  ],
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "*",
        "hooks": [
          {
            "type": "command",
            "command": "node ${CLAUDE_PLUGIN_ROOT}/hooks/pretooluse.js"
          }
        ]
      }
    ]
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 33 lines scan A da1ebe3152f3

Subscribe to this mod's changes

telekey is a plugin published in the GitHub repository stefans71/telekey-mcp (1 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI OAuth Security agent-security capability-based-security mcp rfc8693

telekey

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

emilia-protocol

marketplace

ryk

pegasi

geckovision

signet