Low Risk

github_releases

Latest releases for a GitHub repo (owner/name) — version, date, author, link — via the public releases atom feed (keyless, no rate limit). "What's the newest release of X" — a model can't know releases published after its training cutoff. e.g. repo="facebook/react".

Part of the Dynamic Feed server.

github_releases is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE DYNAMIC FEED →

Free to start. No card required.

AI agents call github_releases to retrieve information from Dynamic Feed without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though github_releases only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "github_releases": {}
  }
}

See the full Dynamic Feed policy for all 50 tools.

Get this rule live on your own Dynamic Feed server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY DYNAMIC FEED →

View all 50 tools →

These attack patterns abuse exactly the kind of access github_releases gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so github_releases only ever does what you allow.

SECURE DYNAMIC FEED →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the github_releases tool do? +

Latest releases for a GitHub repo (owner/name) — version, date, author, link — via the public releases atom feed (keyless, no rate limit). "What's the newest release of X" — a model can't know releases published after its training cutoff. e.g. repo="facebook/react".. It is categorised as a Read tool in the Dynamic Feed MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on github_releases? +

Register the Dynamic Feed MCP server in PolicyLayer and add a rule for github_releases: 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 Dynamic Feed. Nothing to install.

What risk level is github_releases? +

github_releases is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit github_releases? +

Yes. Add a rate_limit block to the github_releases 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 github_releases completely? +

Set action: deny in the PolicyLayer policy for github_releases. 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 github_releases? +

github_releases is provided by the Dynamic Feed MCP server (https://dynamicfeed.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Dynamic Feed tool call.

Deterministic rules across all 50 Dynamic Feed tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.