Seiro MCP is a lightweight MCP server focused on visionOS development workflows for AI coding agents. It enables Codex CLI and other MCP clients to safely build, validate, and inspect visionOS projects through a dedicated set of MCP tools.
The goal of Seiro MCP is not to expose every Xcode capability. Instead, it intentionally focuses on the developer workflows that AI coding agents perform most frequently during day-to-day development. Today it provides visionOS build tools together with bundled Codex skill guidance, and over time it will expand with additional developer-focused utilities for spatial computing while remaining focused on development rather than release management.
Lightweight visionOS development MCP server and skills for AI coding agents.
Estrelas
16
Ferramentas
—
Disponibilidade
—
Features
Focused visionOS development workflows for AI coding agents
Safe build automation through explicit project constraints
AI-friendly MCP interface for build, diagnostics, and artifacts
Codex Skill integration for preferred visionOS build operation
Predictable local development workflow
Written in Rust
Why Seiro MCP?
General-purpose Xcode automation is powerful, but AI coding agents usually need a focused subset of development operations: validate the environment, build a project, inspect failures, and retrieve artifacts.
Seiro MCP keeps that interface intentionally small. Smaller MCP tool surfaces are easier for agents to reason about, easier for humans to review, and safer to run in local development environments. The project prioritizes predictable developer workflows over release automation, signing orchestration, or full Xcode replacement.
Lightweight does not mean fewer features. It means exposing the right capabilities for AI-assisted development while deliberately leaving release-oriented workflows, signing orchestration, and broad Xcode automation outside the project's scope.
MCP_CONFIG_PATH and --config remain available for non-default config locations. When neither is set, Seiro MCP reads seiro-mcp.toml from the process current directory.
The bundled skill name uses the seiro-mcp- prefix to avoid collisions.
The bundled skill canonical source is .agents/skills/seiro-mcp-visionos-build-operator/, including SKILL.md, agents/openai.yaml, and icon assets under .agents/skills/seiro-mcp-visionos-build-operator/assets/.
Use seiro-mcp skill remove seiro-mcp-visionos-build-operator to roll back.
skill remove returns not_found without failing when the skill is already absent.
Verify compatibility with seiro-mcp --version before skill operations.
For this release line, seiro-mcp skill install defaults to seiro-mcp-visionos-build-operator. Passing that skill name explicitly is still supported.
seiro-mcp skill install installs the bundled skill into the local Codex skills directory and does not install the Seiro MCP server binary or configure MCP settings.
Use seiro-mcp --help, seiro-mcp skill --help, and seiro-mcp --version for self-check.
This installs only the Codex skill files. You still need the seiro-mcp binary plus MCP server configuration (seiro-mcp config mcp and seiro-mcp config project).
Usage
Using from Codex CLI
Add an entry like the following to Codex CLI config (~/.codex/config.toml) to call the visionOS tools:
Codex CLI does not expand ${HOME}, so use absolute paths and replace <your-username>.
Prefer seiro-mcp config mcp to print this snippet with the actual installed binary path.
By default, Seiro MCP reads seiro-mcp.toml from the project current directory.
Restart Codex CLI and confirm mcp list shows the visionOS tools.
How It Works
1. Launch the server via an MCP client
The MCP client must spawn the server as a child process and perform the RMCP handshake over stdio. Running cargo run directly without a client will fail immediately.
Example with Inspector:
npx @modelcontextprotocol/inspector seiro-mcp
If you need a non-default config path, pass MCP_CONFIG_PATH=/absolute/path/to/seiro-mcp.toml.
If you are developing from source, build the binary and launch it through an MCP client.
MOCK_XCODEBUILD_BEHAVIOR switches the test fixture (tests/fixtures/visionos/mock-xcodebuild.sh) among success / fail / timeout.
On success, returns job_id, artifact_path, artifact_sha256, log_excerpt, duration_ms; on failure, returns errors such as build_failed or timeout.
If multiple simulators match the destination name, build_visionos_app returns destination_ambiguous with matched_devices, available_destinations, and a retry-ready suggested_destination.
If a build fails, inspect diagnostics without running manual shell commands:
mcp call inspect_build_diagnostics '{
"job_id": "<UUID returned in build error context>",
"include_log_excerpt": true,
"prefer_typecheck": true
}'
availability: "available" returns primary_location (file, line, column) from typecheck diagnostics.
availability: "unavailable" falls back to an xcodebuild_log summary with notes.
4. Download artifacts with fetch_build_output
mcp call fetch_build_output '{
"job_id": "<UUID returned by build_visionos_app>",
"include_logs": true
}'
artifact_zip points to target/visionos-builds/<job_id>/artifact.zip; copy it before download_ttl_seconds expires.
Set include_logs: false to omit log_excerpt and reduce noise on the client side.
Skills Support
Seiro MCP keeps the MCP-only flow unchanged. You can choose either mode:
Skill-assisted mode: use the seiro-mcp-visionos-build-operator skill for Xcode / visionOS project workflows so Codex prefers Seiro MCP over direct xcodebuild / swiftc.
If project_path or scheme is missing in skill-assisted mode, run inspect_xcode_schemes first as optional preflight.
When discovering a project locally, remember that .xcodeproj and .xcworkspace are directory packages. Do not rely on file-only searches such as rg --files to decide they are absent.
--config / MCP_CONFIG_PATH: --config wins; otherwise MCP_CONFIG_PATH -> ./seiro-mcp.toml (relative paths are resolved to absolute).
Token setup is not required for the default local Codex workflow.
Exit codes:
44: MCP_CLIENT_REQUIRED (stdin/stdout is a TTY; must be launched via MCP client)
See the Runbook section "Shutdown procedure and exit codes" for details.
Troubleshooting
Config file not found: run seiro-mcp config project in the project root or set an absolute MCP_CONFIG_PATH.
MCP_CLIENT_REQUIRED: occurs when running cargo run directly; always launch via an MCP client (Inspector / Codex, etc.).
seiro-mcp: command not found: verify installation and use seiro-mcp config mcp to print the Codex MCP snippet.
path_not_allowed: add the project parent to visionos.allowed_paths and restart.
scheme_not_allowed: add the scheme to visionos.allowed_schemes and restart.
sdk_missing: check details.diagnostics first; if probe_mode is env, verify VISIONOS_SANDBOX_SDKS. Then run inspect_xcode_sdks and retry after SDK/config fixes.
build_failed: use job_id from the structured error and call inspect_build_diagnostics to identify file/line before retrying.
As AI coding agents become more capable, they also need reliable ways to interact with local development environments. Existing solutions often aim to expose broad Xcode functionality, but many autonomous development tasks require only a small, well-defined subset of those capabilities.
Seiro MCP started from a simple idea: provide only the tools that are actually needed for AI-assisted visionOS development, and make those tools reliable, secure, and easy for AI agents to use. Rather than becoming a full-featured Xcode automation server, Seiro MCP is designed to be a focused development companion that helps AI agents build, validate, inspect diagnostics, and support spatial computing projects.
The long-term vision is to grow Seiro MCP into a collection of carefully designed developer tools that improve AI-assisted development for visionOS and spatial computing while preserving its lightweight philosophy.
Roadmap
Seiro MCP will continue to grow as a focused development toolkit for AI-assisted spatial computing work. Planned directions include:
Additional visionOS developer tools
Project analysis utilities
Additional development workflows for visionOS
Swift Package support
Better AI agent workflow guidance
More spatial computing developer utilities
The roadmap remains aligned with the lightweight philosophy: Seiro MCP should expose the right development tools for AI agents, not become a full-featured Xcode MCP server.
Unit tests in src/server/config/mod.rs cover configuration validation (success and error cases).
tests/integration/visionos_build.rs covers validate_sandbox_policy, build_visionos_app, inspect_build_diagnostics, and fetch_build_output, including TTL behavior.
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Perguntas
Como instalo Seiro?
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Seiro precisa de uma chave de API?
Este registro não lista nenhuma variável de ambiente obrigatória.
Qual transporte Seiro usa?
Seiro roda localmente via stdio.
Quando Seiro foi verificado pela última vez?
Última verificação: 2026-11-05. Lightweight visionOS development MCP server and skills for AI coding agents.