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.

What is an MCP-based agent?

An MCP-based agent is a Large Language Model that runs in a loop inside a harness and acts through Model Context Protocol (MCP) tools. In the HAPI MCP stack, the tools come from your OpenAPI and Arazzo contracts, the harness is OrcA or your agent platform, and a role narrows the agent to a job.

Do I need to write code to give an agent tools from my API?

No. HAPI reads an OpenAPI 3.x or Arazzo 1.1 contract and serves each operation or workflow as an MCP tool. With --headless --url, HAPI forwards each tool call to your existing backend, so the contract is the whole integration.

What is an agent harness, and what does OrcA do?

A harness prepares the instructions, context, and tool definitions for the model, applies approvals, routes tool calls, and records what happened. OrcA is a VS Code harness for MCP and API work: it connects models to MCP servers, loads tools progressively, asks before tools that are not read-only, and shows every exchange in its Traffic view. It does not edit files or run a terminal.

How do I stop an agent from loading too many tools?

Serve the contract with --capability-graph or --deferred-tool-search. HAPI defers operation tools behind a tool_search tool, and OrcA loads only the tools each message needs, while listing the names of the rest so the model knows they exist.

How do I test an MCP agent before production?

Test plans offline with hapi graph audit and hapi graph simulate, then test conversations in OrcA. The Context tab shows goals, required facts, and gates, and the Traffic view shows each model round and tool call with latency, tokens, and cost.

How do I deploy an MCP server built from an OpenAPI contract?

Run hapi deploy with an HTTPS contract URL and your backend URL to deploy a headless MCP server to Cloudflare Workers, or select Deploy MCP Server on the contract in OrcA.

What is MCP context bloat, and how do I avoid it?

Context bloat happens when an MCP server sends every tool definition with every request, so the model spends its context on tools it never uses and picks the wrong one more often. Serve the contract with --capability-graph or --deferred-tool-search, and let a harness such as OrcA load tools progressively.

What is progressive tool discovery?

Progressive tool discovery sends a small search tool and a few always-loaded tools instead of the full catalog. OrcA loads matching tools before the model answers each message, lists the names of the remaining tools so the model knows they exist, and appends discovered tools without reordering them, which keeps prompt caches valid.

What are the x-hapi extensions in OpenAPI?

They are OpenAPI extensions that HAPI compiles into its capability graph: x-hapi-capability and x-hapi-intent for discovery, x-hapi-effects and x-hapi-prerequisites for behavior, x-hapi-planning for state transitions, x-hapi-client-facts for facts people establish, x-hapi-outcome for failure responses, and x-hapi-event for webhooks.

Why does capability_plan always return clarification-required?

Usually because some required facts are never produced by an operation and are not declared as client facts. Run hapi graph audit to list these orphan requirements, then declare selections, confirmations, and identity checks in x-hapi-client-facts.

Why does every search tool ask for confirmation?

HAPI marks every POST, PUT, PATCH, and DELETE operation as destructive unless the contract sets tool hints, and clients such as OrcA ask before any tool that is not read-only. Add x-readOnlyHint: true and x-destructiveHint: false to read-only searches that use POST.

Does HAPI tool search work across languages?

No. HAPI search matches words in tool names, descriptions, and arguments. Write summaries in the language of your users, or add their terms to descriptions; OrcA's catalog of tool names reduces, but does not remove, the impact of a language mismatch.

What is an intent-based API?

An intent-based API contract adds a decision layer to an API description: when each operation applies, what it changes, which verified facts it requires and produces, and what a failure means. HAPI compiles this metadata into a capability graph, so an agent can map a request to a goal and receive a deterministic plan that names the missing information.

Are Arazzo workflows and HAPI intent-based contracts redundant?

No. Arazzo workflows encode fixed sequences that must always run together. Intent-based contracts let a planner decide which atomic operations, and which workflows, to run from the current state. A workflow with x-hapi-planning becomes one atomic step in those plans.

Are Arazzo workflows all-or-nothing?

No. An Arazzo workflow stops at the first step whose success criteria fail, but earlier steps have already changed state in the source API. Neither Arazzo nor HAPI undoes earlier steps automatically, so compensation is a design decision.

Are API workflows idempotent?

Only when every step is idempotent or carries an idempotency key. A step that creates a record with a new identifier is not idempotent, so running the workflow twice creates two records.

Is an OpenAPI description enough for AI agents?

It is enough to call an API, not to use it safely. OpenAPI describes paths, schemas, status codes, and security, but not when an operation is the right choice, what it changes, what must already be true, or what a failure means for the next step.

Does intent-based planning stop LLM hallucinations?

It limits their impact. The model still interprets the request, but permissions, prerequisites, ordering, and confirmations come from the contract and are enforced deterministically. The planner never invents facts; it accepts only facts the client verified and reports the missing ones.

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.

7 publicaciones etiquetados con "Tool Calling"

Tool calling refers to the ability of AI models to invoke external tools or APIs to perform specific tasks or retrieve information, enhancing their functionality and capabilities.

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).

How to Build and Manage MCP-Based Agents from Your API Contracts

What you will learn

How to build an MCP-based agent without writing tool code.
How to define capabilities in OpenAPI 3.x contracts with intent-based planning.
How to give the agent a transparent harness in VS Code.
How to test, measure, deploy, and manage an MCP-based agent over time.

How to Design OpenAPI Contracts That Guide AI Agents

What you will learn

How to enrich an OpenAPI contract for progressive tool discovery.
How to declare effects, intent, and planning facts for AI agents.
How to model business state and human-established facts.
How to audit, simulate, and serve the capability graph.
How to verify agent behavior in VS Code.

How to Make Intent-Based Contracts and APIs AI-Ready

What you will learn

How intent-based planning balances model interpretation with deterministic enforcement.
How to make an OpenAPI contract intent-based AI contract.
How to verify contracts and workflows.
How to observe re-planning behavior in VS Code.

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.

OpenAI SDK Meets MCP (Model Context Protocol)

An evolution of tool calling with MCP, thanks to OpenAI's latest SDK updates.

Step-by-step, I'll guide you through setting up an MCP server, integrating it with the OpenAI SDK, and running a complete example that showcases dynamic tool calling. By the end of this post, you'll be equipped to leverage MCP in your own OpenAI-powered applications.