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.
npx skills add andrea-magni/MARS --skill mars-mcp-servergit clone --depth 1 https://github.com/andrea-magni/MARSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/andrea-magni/mars/mars-mcp-server)<a href="https://agentmods.dev/skills/andrea-magni/mars/mars-mcp-server"><img src="https://agentmods.dev/badge/skills/andrea-magni/mars/mars-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/andrea-magni/mars/mars-mcp-server"><img src="https://agentmods.dev/badge/skills/andrea-magni/mars/mars-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 101 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00172 | $0.01996 |
| Opus 5 | $0.00086 | $0.00998 |
| Sonnet 5 | $0.00034 | $0.00399 |
| Haiku 4.5 | $0.00017 | $0.00200 |
Grade A, and why
mars-mcp-server scanned grade A with 1 finding 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 12d ago.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
With curl (initialize / list / call): How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build an MCP server with MARS-Curiosity
MARS ships native MCP support (units MARS.MCP.* in Source/): derive a resource from TMCPResource, mark methods with [MCPTool], and any MARS server becomes an MCP server speaking the Streamable HTTP transport (single endpoint, JSON-RPC 2.0 over POST). Tool list and JSON Schema are generated from RTTI — no protocol code to write.
The complete working example is Demos/MCPServer in the MARS repository (public tools + FireDAC-backed authenticated tools + OAuth).
Minimal MCP server
unit Server.Resources.MCP;
interface
uses
SysUtils, Classes
, MARS.Core.Attributes, MARS.Core.MediaType
, MARS.MCP.Resource, MARS.MCP.Attributes;
type
TCalculationResult = record
operation: string;
value: Double;
end;
[Path('mcp')
, MCPServerInfo('My MCP Server', '1.0.0'
, 'Optional instructions the AI agent reads on connection.')]
TMyMCPResource = class(TMCPResource)
public
[MCPTool('say_hello', 'Returns a friendly greeting for the given name')]
function SayHello(
[MCPParam('name', 'Name of the person to greet')] const AName: string): string;
[MCPTool('add_numbers', 'Adds two numbers and returns a structured result')]
function AddNumbers(
[MCPParam('a', 'First operand')] const A: Double;
[MCPParam('b', 'Second operand')] const B: Double): TCalculationResult;
end;
implementation
uses
MARS.Core.Registry;
function TMyMCPResource.SayHello(const AName: string): string;
begin
Result := 'Hello, ' + AName + '!';
end;
function TMyMCPResource.AddNumbers(const A, B: Double): TCalculationResult;
begin
Result.operation := 'add';
Result.value := A + B;
end;
initialization
MARSRegister([TMyMCPResource]);
end.
This is a regular MARS resource: register the unit mask in Server.Ignition.pas as usual (AddApplication('DefaultApp', '/default', ['Server.Resources.*'])). The MCP endpoint is the composed URL, e.g. http://localhost:8080/rest/default/mcp. Everything the mars-development skill says about resources, [Context] injection and configuration applies here too.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 128 lines · 172 tokens per session scan A bd9531bcf734
mars-mcp-server is a skill published in the GitHub repository andrea-magni/MARS (394 stars, last pushed 21d ago), licensed MPL-2.0. It adds 172 tokens to every session and 1,996 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
horse-mvc-architecture
Guide for structuring corporate Horse applications using Clean MVC (Model-View-Controller) principles and decoupling HTTP layers from business logic.
horse-request-response
Guide to interacting with THorseRequest (body, query, params, headers) and THorseResponse (Send, Status, ContentType).
horse-dependency-injection
Guide for managing request-scoped contextual services and IoC (dependency injection) in Delphi and Lazarus.
horse-integration-tests
Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.
horse-performance-tuning
Guide for optimizing performance, tuning memory alocations, handling large payloads, and adjusting provider execution pipelines.