net-mcp

Local Curl

local_curl

Run HTTP requests from the local machine to test connectivity, inspect headers, TLS certificates, and response codes from the local network perspective.

Instructions

Make an HTTP request from the local machine using curl.

Useful for testing connectivity, checking HTTP headers, TLS certificates, and response codes from the local network perspective. Output is capped at 10,000 characters (the note field says when it was truncated). Does not require admin privileges.

curl runs with -q (ignores ~/.curlrc) and -g (no URL globbing, so brackets and braces in the URL are literal and cannot fan out into many requests). Only http:// and https:// URLs are accepted.

Disabled by default. When enabled via allow_active_tools this tool deliberately does NOT block private, loopback, link-local or cloud metadata addresses (for example 127.0.0.1, 10.0.0.0/8 or 169.254.169.254): reaching internal endpoints from this host is part of its purpose as a local diagnostic, and operators who enable it accept that trade-off.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	URL to fetch (e.g. 'https://example.com'). https:// is assumed when no scheme is given.
`timeout`	No	Request timeout in seconds (1-120)
`head_only`	No	Only fetch headers, not body
`follow_redirects`	No	Follow HTTP redirects (at most 5)

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	Additional context about the result
`error`	No	Why the tool could not produce a result: input validation failure, tool disabled by configuration, binary not installed, or no service answered. Empty when the command executed.
`stderr`	Yes	Standard error of the command, or the failure message when the command did not run
`stdout`	Yes	Standard output of the command (curl output is capped at 10,000 characters)
`command`	Yes	The exact command line that was executed, or the tool name if the command never ran
`success`	Yes	True when the command ran and exited with status 0
`platform`	Yes	Operating system the command ran on (Darwin, Linux or Windows)
`returncode`	Yes	Process exit status. 0 = success; 2 = input rejected before running; 124 = timed out; 126 = disabled by config or permission denied; 127 = binary not found

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 22, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden and delivers: output truncation at 10,000 characters, no admin privileges required, -q and -g curl flags, only http/https URLs accepted, and deliberate non-blocking of private/loopback/metadata addresses. This is unusually rich behavioral disclosure for a tool definition.

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?

The description is longer than average, but every sentence earns its place: purpose, use cases, output limits, permission requirements, curl behavior, URL constraints, and security trade-offs. Information is front-loaded and structured logically from general purpose to operational details.

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

Completeness5/5

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

Given the output schema (which explains return values) and the high parameter schema coverage, the description is complete enough for an agent to select and invoke this tool correctly. It covers safety-relevant behavior (private addresses), operational constraints (truncation, disabled by default), and URL restrictions, leaving no critical gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful nuance beyond the schema by explaining URL scheme restrictions, -g globbing behavior for bracket/brace URLs, and the output cap. It does not add much for timeout, head_only, or follow_redirects, but the URL-related behavior is a genuine value-add.

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 states a specific verb and resource: 'Make an HTTP request from the local machine using curl.' It clearly differentiates this tool from local networking siblings like ping, traceroute, or DNS tools by focusing on HTTP/S inspection through curl, and further lists concrete use cases (connectivity, headers, TLS certs, response codes).

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 description gives clear context about when to use the tool: for testing connectivity, checking HTTP headers, TLS certificates, and response codes from the local network perspective. It does not explicitly name alternative tools or exclusions, so it misses the top bar of explicit when-not/alternatives, but the use-case context is strong.

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