Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@OrcaSlicer MCP Server Slice gear.stl using the PETG profile and check the estimated print time"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OrcaSlicer を AI エージェントから操作するための MCP (Model Context Protocol) サーバーです。
プロファイルの探索・設定変更・スライス実行・G-code 解析までを、 Claude などの AI アシスタントを通して安全に行えます。
やりたいこと | 使うツール |
どんなプロファイルがあるか確認したい |
|
設定項目をキーワードで探したい |
|
プロファイルの中身を読みたい |
|
印刷設定を調整したい |
|
STL/3MF をスライスしたい |
|
G-code の印刷時間やフィラメント量を確認したい |
|
サーバーの動作環境を診断したい |
|
Related MCP server: cura-mcp
# 1. インストール & ビルド
npm install && npm run build
# 2. 起動（カレントディレクトリが作業フォルダになります）
npm start
# 作業フォルダを指定して起動する場合
npm start -- --workdir="./my_3d_projects"ドキュメント | 内容 |
OS 別のインストール手順、OrcaSlicer の準備 | |
環境変数、 | |
全 7 ツールの引数・戻り値・使い方 | |
「探索→調整→スライス→評価」の具体例 | |
サンドボックス、ファイル保護の仕組み | |
よくあるエラーと解決方法 |
Node.js 18 以上
Windows 11 / macOS (Intel & Apple Silicon)
OrcaSlicer がインストール済みであること
AGPL-3.0
Parse metadata (estimated time, filament usage, cost, layers) from a G-code file and return structured JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| file | Yes | G-code filename (in work directory). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool parses metadata and returns JSON, but lacks details on error handling (e.g., invalid file), performance (e.g., processing time), or side effects (e.g., file access). This leaves gaps for a tool that reads and processes files.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core action ('parse metadata') and includes all essential details (target, output, metadata types). There is no wasted verbiage, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (file parsing), no annotations, and no output schema, the description is minimally adequate but incomplete. It covers the purpose and output format but lacks behavioral context (e.g., errors, limitations) and detailed usage guidelines, which are needed for a tool with file operations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the 'file' parameter as a G-code filename in the work directory. The description adds no additional parameter semantics beyond what the schema provides, such as file format requirements or examples, meeting the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('parse metadata'), the target resource ('G-code file'), and the output format ('structured JSON'), distinguishing it from siblings like slice_model or list_profiles. It explicitly lists the types of metadata extracted (estimated time, filament usage, cost, layers), making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like slice_model or search_settings, nor does it mention prerequisites (e.g., file must exist in work directory) or exclusions. Usage is implied by the action but not explicitly contextualized relative to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read and return the full JSON content of a profile file.
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | Profile category. | |
| name | Yes | Profile filename (with .json extension). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states this is a read operation, implying it's non-destructive, but lacks details on permissions, error handling, rate limits, or return format (beyond 'full JSON content'). This is insufficient for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core functionality ('Read and return the full JSON content'). There is zero waste, making it highly concise and well-structured for quick understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is minimally adequate. It covers the basic action but lacks details on behavioral traits, usage context, and output specifics, leaving gaps that could hinder effective tool invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no parameter semantics beyond what the input schema provides, which has 100% coverage with clear descriptions for both parameters. The baseline is 3 since the schema does the heavy lifting, but the description doesn't compensate with additional context like file location or JSON structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Read and return') and resource ('full JSON content of a profile file'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this tool from sibling tools like 'list_profiles' or 'update_profile_setting', which would require a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'list_profiles' (which might list available profiles) or 'update_profile_setting' (which might modify profiles), leaving the agent without context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Diagnose the server environment: check if the OrcaSlicer binary is reachable and if the settings/work directories are accessible.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It describes what the tool checks (binary reachability, directory accessibility) but doesn't disclose critical behavioral traits: what permissions are required, whether it performs active tests or passive checks, what happens if checks fail (errors vs. warnings), or what the output format will be. For a diagnostic tool with zero annotation coverage, this leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose ('diagnose the server environment') followed by specific checks. Every word earns its place with no redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's diagnostic nature, no annotations, and no output schema, the description is incomplete. It doesn't explain what the output will contain (e.g., status codes, detailed error messages, structured results), how to interpret results, or what actions might follow from the diagnosis. For a tool that presumably returns important system information, this is inadequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters with 100% schema description coverage, so the schema already fully documents the absence of parameters. The description appropriately doesn't discuss parameters, which is correct for a parameterless tool. Baseline for zero parameters is 4, as there's nothing to compensate for.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('diagnose', 'check') and resources ('server environment', 'OrcaSlicer binary', 'settings/work directories'). It distinguishes from siblings by focusing on system health rather than slicing operations or profile management. However, it doesn't explicitly differentiate from all siblings (e.g., 'search_settings' might overlap conceptually).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context ('diagnose the server environment') suggesting this tool should be used for system troubleshooting. However, it provides no explicit guidance on when to use this versus alternatives, no prerequisites, and no comparison to sibling tools like 'search_settings' which might also reveal accessibility issues.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List available profile files for a given category (machine, filament, or process).
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | Profile category to list. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states it's a list operation, implying read-only behavior, but doesn't mention pagination, sorting, filtering beyond category, output format, or error conditions. This leaves significant gaps for a tool that likely returns multiple items.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core action and resource, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a list operation with no annotations and no output schema, the description is incomplete. It doesn't explain what the output contains (e.g., profile names, IDs, metadata), how results are structured, or any limitations like maximum items returned. This leaves the agent guessing about the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the single parameter 'type' fully documented in the schema (including enum values). The description adds minimal value by restating the parameter's purpose ('for a given category') without providing additional context like default behaviors or examples.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('list') and resource ('profile files'), specifying the scope ('for a given category') with three enumerated categories. It distinguishes from siblings like 'get_profile_content' (which retrieves content) and 'update_profile_setting' (which modifies settings), but doesn't explicitly contrast with 'search_settings' which might overlap in listing functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'search_settings' or 'get_profile_content'. It mentions the category parameter but doesn't explain prerequisites, limitations, or typical use cases beyond the basic function.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for setting keys containing a keyword across all (or a specific type of) profiles. Useful when you don't know the exact key name — e.g. query "infill" returns all infill-related settings and their current values.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Keyword to search (e.g. "infill", "speed"). | |
| type | No | Optionally limit search to a profile type. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the search behavior (fuzzy matching on keywords) and output format (returns settings and their current values), but lacks details on permissions, rate limits, pagination, or error handling. The description adds useful context beyond the schema but doesn't fully compensate for the absence of annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise with two sentences that each earn their place: the first defines the tool's purpose and scope, the second provides usage guidance with a concrete example. No wasted words, and information is front-loaded appropriately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is reasonably complete. It explains what the tool does, when to use it, and what to expect in results. However, without annotations or output schema, it could benefit from more behavioral details like response format specifics or limitations. The description compensates well but has minor gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description adds marginal value by providing an example ('e.g. query "infill" returns all infill-related settings') that illustrates parameter usage, but doesn't add significant semantic information beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('search for setting keys containing a keyword'), identifies the resource ('across all (or a specific type of) profiles'), and distinguishes it from siblings by focusing on fuzzy keyword search rather than exact key operations. It provides a concrete example ('query "infill" returns all infill-related settings and their current values') that reinforces the purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use this tool ('Useful when you don't know the exact key name') and implies alternatives by contrasting with sibling tools like 'get_profile_content' or 'update_profile_setting' that might require exact keys. It also provides context about optional filtering by profile type, guiding usage decisions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run OrcaSlicer CLI to slice a model file. Specify input/output filenames and optionally profiles to use.
| Name | Required | Description | Default |
|---|---|---|---|
| input_file | Yes | STL / 3MF input filename (in work directory). | |
| output_file | Yes | Desired G-code output filename. | |
| profile_machine | No | Machine profile filename (optional). | |
| profile_filament | No | Filament profile filename (optional). | |
| profile_process | No | Process profile filename (optional). | |
| timeout_ms | No | Timeout in milliseconds (default 300000). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'slice a model file' (implying a processing action) and a timeout parameter, but lacks details on permissions, side effects (e.g., file creation/deletion), error handling, or output format (G-code specifics). This is insufficient for a tool with potential file system impacts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, consisting of a single sentence that directly states the tool's purpose and key parameters. Every word contributes to understanding without redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is incomplete. It doesn't explain the output (G-code file details), error conditions, or behavioral traits like whether it modifies input files or requires specific environment setups. Given the complexity of slicing operations, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all parameters. The description adds minimal value by summarizing parameters ('input/output filenames and optionally profiles'), but doesn't provide additional context like file format constraints or profile interactions beyond what's in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Run OrcaSlicer CLI to slice a model file.' It specifies the verb ('slice') and resource ('model file'), though it doesn't explicitly differentiate from sibling tools like 'analyze_gcode_metadata' or 'list_profiles'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description mentions optional profiles but doesn't specify prerequisites, dependencies, or scenarios where other tools might be more appropriate, such as using 'get_profile_content' for profile details first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update a single setting key in a profile. By default (dry_run=true), the change is saved to a _tuned copy rather than overwriting the original.
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | Profile category. | |
| name | Yes | Profile filename. | |
| key | Yes | Setting key to update. | |
| value | Yes | New value for the setting. | |
| dry_run | No | If true (default), saves as a _tuned copy instead of overwriting. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context about the dry_run behavior (saving to a tuned copy vs. overwriting), which is a key trait. However, it lacks details on permissions, error handling, or response format, leaving gaps for a mutation tool. No contradiction exists as annotations are absent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose and includes a crucial behavioral detail in a single, efficient sentence. Every word earns its place, with no redundancy or unnecessary elaboration, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity as a mutation tool with 5 parameters and no output schema, the description is moderately complete. It covers the purpose and key behavior (dry_run), but lacks details on return values, error cases, or integration with sibling tools. With no annotations, it should do more to compensate, but it's adequate for basic understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by reiterating the dry_run default behavior, but doesn't provide additional meaning or examples for parameters like 'type' or 'value'. Baseline 3 is appropriate given high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'update' and the resource 'a single setting key in a profile', making the purpose specific and understandable. However, it doesn't explicitly differentiate this tool from potential siblings like 'search_settings' or 'get_profile_content', which might handle similar profile data but with different operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by mentioning the default behavior (dry_run=true saves to a tuned copy), which suggests this tool is for modifying profile settings. However, it doesn't provide explicit guidance on when to use this vs. alternatives like 'search_settings' or 'list_profiles', nor does it specify prerequisites or exclusions, leaving the context somewhat vague.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v2.0.0analyze_gcode_metadataget_profile_contenthealth_checklist_profilessearch_settingsslice_modelupdate_profile_settingScored across 7 tools
Each tool has a clearly distinct purpose with no overlap: analyze_gcode_metadata parses G-code files, get_profile_content reads profiles, health_check diagnoses the server, list_profiles enumerates profiles, search_settings finds settings, slice_model performs slicing, and update_profile_setting modifies profiles. The descriptions clearly differentiate their functions, making misselection unlikely.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., analyze_gcode_metadata, get_profile_content, slice_model). The verbs are descriptive and appropriate for each action, and there are no deviations in naming conventions across the set.
With 7 tools, the count is well-scoped for an OrcaSlicer server, covering essential operations like slicing, profile management, and diagnostics. Each tool serves a clear purpose without redundancy, and the number is manageable for agents to navigate effectively.
The tool set provides strong coverage for core 3D printing workflows, including slicing, profile handling, and G-code analysis. A minor gap is the lack of tools for creating or deleting profiles, which might require workarounds, but the existing tools support most common tasks without dead ends.
Parametric 3D CAD for AI agents: build print-ready parts, check them, export STL, 3MF or STEP.
Real 3D-print slicing, quoting, DFM, orientation & material/settings advisors. Free personal tier.
3D print farm management for AI. Monitor, queue, and control prints on your SimplyPrint account.
Independent directory of agentic AI tools — search, compare & recommend via MCP. Read-only.
