Skip to main content
Glama
Sign In

Fivebar Trading

by io.github.fivebar-xyz
OverviewDiscussionsAdmin

Is this MCP server safe to connect?

mcp_check
Read-only

Before connecting an MCP server to your agent: give its URL (remote) or the package that runs it (npx @scope/server, uvx name). A remote server is connected to like a client (initialize, tools/list, no credentials) and every tool is read for what it can do (move money or sign, run code, files, web, messages, change or delete things), secrets it asks for as arguments, and tool poisoning: descriptions with instructions aimed at the model (ignore your instructions, don't tell the user, blocks, read ~/.ssh or .env, hidden characters). Plus whether it's in the official MCP registry and its domain's age and phishing-list status. A local server's package gets package_check. Verdict: high risk, caution, no warnings, or needs sign-in, with the list of what it can do.

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": {
      "server": "<server>"
    },
    "name": "mcp_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
serverYesThe MCP server's https URL, or the command/package that runs it (npx @scope/server)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it explains that a remote server is connected to like a client (initialize, tools/list) with no credentials sent, that each tool is read for risk categories, and that network-side signals (registry membership, domain age, phishing lists) are checked. It also names the verdict vocabulary, all of which an agent needs in order to interpret and trust the result.

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

Conciseness3/5

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

The lead clause is well front-loaded, but the body is a single sprawling run-on sentence built from nested parentheticals and comma lists, which forces re-reading. The content mostly earns its place; the packaging does not.

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 one-parameter scan with no output schema, the description covers the scan scope, the connection method, and the shape of the verdict, so an agent can act and interpret without guessing. It stops short of stating runtime, whether results are cached, or what the 'needs sign-in' path requires next.

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?

With one parameter and 100% schema description coverage, the schema already defines the accepted formats, and the description largely restates them, adding only the 'uvx name' variant. Baseline 3 is appropriate: the description reinforces but does not materially extend the parameter contract.

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?

States a specific verb and resource ('check' an 'MCP server' for safety before connecting) and enumerates exactly what is inspected: tool capabilities, requested secrets, tool poisoning, registry presence, domain age, phishing status. It also distinguishes itself from the sibling package_check, with which it could otherwise be confused, by routing local packages there.

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?

The trigger is explicit and front-loaded: use it 'before connecting an MCP server to your agent', and supply either a remote URL or the command that runs it. It names the alternative (package_check) for local server packages. The boundary is slightly blurred because mcp_check itself accepts an npx package argument, so the agent must infer when a package should go to one tool versus the other.

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

All Fivebar Trading toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources