What are the Ask, Plan and Act roles in OrcA?

They are chat roles that decide what an AI agent may do with your MCP servers. In Ask, the model only receives read-only tools and answers questions. In Plan, it also uses capability planning and ends with a numbered plan, without changing anything. In Act, it receives every tool, and changes still ask for your approval by default.

Why use roles if I already have a capability graph?

The capability graph describes what the API needs and in what order; it is read-only advice and never prevents a tool call. The role decides what the agent may do in this conversation. In Ask and Plan, tools that change data are never sent to the model, so it cannot call them. Roles also work with servers that have no capability graph.

Is a role just an instruction in the prompt?

No. OrcA enforces roles in the tools it sends: hidden tools are removed from the request, from the deferred tool catalog and from search results, and a call to one is refused with a message naming the role. The instructions only explain the role to the model.

When should I use Ask, Plan or Act?

Use Ask to explore an API or test a new server with zero risk. Use Plan before multi-step or irreversible actions, to review the steps, missing information and confirmations first. Use Act when the steps are clear, typically after Plan with the Proceed button.

How do roles relate to tool approvals?

The role decides which tools exist for the model; approvals decide when OrcA asks you before using them. In Act, the default preset asks before any tool that may change data, and workspace rules can always allow or never allow a specific tool.

What is an agent harness?

An agent harness is the software layer that runs an agent session. It prepares the instructions, context and tool definitions for the language model, applies approval rules, routes tool calls, and records what happened. OrcA 0.4 is a harness specialised for MCP and API work inside VS Code; it does not edit files or run a terminal.

What is progressive tool discovery in MCP?

Instead of sending every tool definition on every turn, the client sends a small search_tools tool plus a list of tool names, and loads full definitions only when they are needed. OrcA 0.4 searches with each message you send, loads matching tools before the model answers, appends them so prompt caches keep working, and resets them on New Chat.

How do I reduce MCP context bloat?

Serve your API with a search tool (for HAPI, --deferred-tool-search or --capability-graph) and keep orca.chat.toolDiscovery on auto, or set it to always to let OrcA search any server locally. The Harness tab shows the tokens your tools cost upfront compared with the full catalog.

Can OrcA connect to MCP servers not built with HAPI?

Yes. Use Add External MCP Server… with a name, a Streamable HTTP URL and optional headers, or Import MCP Servers… from .vscode/mcp.json and your user mcp.json. External servers get chat, traffic, proxy capture and Add to VS Code. stdio and SSE servers are not supported.

Can I get an OpenAPI contract for a hand-written MCP server?

Yes. Generate Contract infers a deterministic OpenAPI 3.1 document from a connected server's tools, resources, resource templates and prompts. It is linked to the server, so Open Operation in Contract works, and OrcA marks the contract out of date when the server's tools change.

Does OrcA 0.4 support OAuth-protected MCP servers?

Not yet. OrcA connects with static headers, such as a bearer token or an API key, stored in VS Code's secret storage. OAuth support is planned.

How do I debug an MCP server in VS Code?

Install OrcA 0.3, right-click a running server in the MCP Servers view and choose Connect, then run OrcA: Show Traffic. Every JSON-RPC request, response and notification appears in a live timeline with latency, size and status. You can open any payload as JSON, diff two calls, copy a call as cURL, and replay it.

How can I see what GitHub Copilot sends to my MCP server?

In OrcA, right-click the server and choose Expose via Proxy, then Add to VS Code and pick Through OrcA (captured). OrcA registers a local proxy address (http://127.0.0.1:7331/mcp/ ) in .vscode/mcp.json. Copilot keeps working as usual, and every request it sends shows up in OrcA Traffic with the client name.

Can I chat with my MCP server without an API key?

Yes. OrcA's Chat can use the language models VS Code makes available to extensions, such as GitHub Copilot's models, which need no extra key. OpenAI, Anthropic, Groq, OpenRouter, Ollama, LM Studio and any OpenAI-compatible endpoint are also supported; their keys are stored in VS Code's secret storage.

Is OrcA an alternative to MCP Inspector?

For day-to-day work inside VS Code, yes. OrcA connects to several MCP servers at once, lists their tools, resources and prompts, lets an LLM use them in a chat, and records both the LLM rounds and the MCP tool calls in one correlated graph. It also captures traffic from other MCP clients through a local proxy. Calling a single tool by hand from a form is planned for a later release.

Does OrcA send my traffic or prompts anywhere?

No. OrcA has no telemetry and no vendor SDKs. Traffic stays in memory with secrets redacted, the chat only contacts the LLM provider you selected, the proxy listens on 127.0.0.1 only, and nothing is written to disk unless you save a session file.

Does OrcA support OAuth-protected MCP servers?

Not yet. OrcA 0.3 connects with static headers such as a bearer token (Set Headers…). OAuth-protected servers are detected and reported; OAuth support is planned for an upcoming release.

6 publicaciones etiquetados con "LLM"

Large Language Models (LLMs) are advanced AI models trained on vast text data to understand and generate human-like language.

Ver Todas las Etiquetas

Ask, Plan, Act: Agent Roles That Decide What Your MCP Agent May Do

An AI agent with access to your API can read data and change it. The question is not whether it can do something, but whether it should, right now. OrcA answers that with three roles: Ask, Plan and Act. You choose how much the agent may do in each conversation, and OrcA enforces it in the tools the model receives, not only in its instructions.

OrcA 0.4: An MCP Agent Harness in VS Code, for Any MCP Server

OrcA 0.4 turns VS Code into an agent harness for MCP and API work. Connect any Streamable HTTP MCP server, not only HAPI ones. Let the agent load tools as the conversation moves instead of drowning in 40 schemas per turn. Read and edit exactly what the model is told, and see the goals, facts and plans behind a multi-step request. Still free, still no telemetry (by default).

OrcA 0.3: See Every MCP Tool Call and LLM Round in VS Code

OrcA 0.3 lets you see exactly what your AI agent does with your MCP servers, without leaving VS Code. Chat with your servers using the model you already have, watch every LLM round and every MCP tool call in a live Git-style graph, and capture what GitHub Copilot or Claude send to your server. No telemetry, no extra app, no code changes.

Integrate the OpenAI UI SDK for ChatGPT With MCP in 60 Seconds

You want your API to be instantly usable inside AI assistants like ChatGPT, and Web UIs. The OpenAI UI SDK plus the Model Context Protocol (MCP) lets you expose your API as structured tools that large language models can call directly.

Composable Architectures and the Future of AI Integration: Why MCP Is the Missing Link

For years, OpenAPI (OAS) has been the cornerstone of how we describe, document, and integrate APIs. It standardized how systems talk to each other — and in many ways, it made the modern internet possible.

So when the Model Context Protocol (MCP) appeared, some developers were skeptical. "Another spec?" they asked. "Why do we need this when we already have OAS?"

Using OpenAI Response API for MCP Integration

This guide demonstrates how to use the OpenAI Response API to integrate with the Model Context Protocol (MCP) for seamless, AI-driven API interactions. You will learn how to generate a REST API specification with Postman's AI Agent, deploy it as an MCP server using HAPI Server, and connect it through OpenAI's Response API for testing.