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 agentmods add skills/delphi-blocks/claude-plugins/mcpconnect-devnpx skills add delphi-blocks/claude-plugins --skill mcpconnect-devgit clone --depth 1 https://github.com/delphi-blocks/claude-pluginsWhat 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 | $0.00206 | $0.01918 |
| Opus 5 | $0.00103 | $0.00959 |
| Sonnet 5 | $0.00041 | $0.00384 |
| Haiku 4.5 | $0.00021 | $0.00192 |
Grade A, and why
mcpconnect-dev 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 2d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developing with MCPConnect
MCPConnect turns ordinary Delphi classes into an MCP server. You annotate methods with attributes, register the classes in a fluent configuration block, and the framework does the rest: it walks the RTTI, generates JSON schemas via Neon, binds incoming JSON arguments to your parameters, and serializes whatever you return into MCP content.
Two things must always line up, and forgetting either one is the single most common failure:
- the attribute on the method (what the tool/resource/prompt looks like to the client), and
- the registration of its class in the config block (whether the server knows the class exists at all).
An annotated class that is never registered is invisible. A registered class with no annotated methods contributes nothing.
Which reference to read
Read the reference file that matches the task before writing code — these files carry signatures verified against Source/, and the published documentation is known to lag behind the code.
| Task | Read |
|---|---|
New server project, choosing a transport, wiring .dpr / WebModule / form, project search paths |
references/server-setup.md |
| Adding or changing tools: attributes, parameters, return types, tags, error reporting, programmatic registration | references/tools.md |
Resources, resource templates (res://items/{id}), MCP App UIs, static files, prompts |
references/resources-prompts.md |
Sessions, [Context] injection, server→client notifications and SSE, memory ownership, content writers, Neon tuning |
references/sessions-notifications.md |
| Static bearer tokens, OAuth 2.1 resource server, JWT validation, CORS | references/security.md |
For anything not covered there, read the unit in Source/ directly — MCPConnect.Configuration.MCP.pas is the config surface, MCPConnect.MCP.Attributes.pas the attribute list, MCPConnect.MCP.Types.pas the protocol types. The Demo/MCPServer folder is a working server exercising nearly every feature and is the best place to copy a pattern from.
What ships with it
5 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.
- 2d ago First seen · 108 lines · 206 tokens per session scan A 919eb38109e1
mcpconnect-dev is a skill published in the GitHub repository delphi-blocks/claude-plugins (2 stars, last pushed 18d ago), licensed MIT. It adds 206 tokens to every session and 1,918 once invoked, about $0.0010 per session on Opus 5. 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…