DIS
Compile full-stack apps from one architecture spec, with a shared Memory Fabric across agents.
What it can do
- Compile Adl: Compile ADL through DIS V18. Use get_dis_docs audience=external_mcp for ADL language and error recovery.
- Create Requirement: Create a requirement mission and mark it spec_ready
- Download Artifact: Download workspace artifact
What data it sees
Do you need an account
No: the server works without sign-in
Compile full-stack apps from one architecture spec, with a shared Memory Fabric across agents.
How to connect
How to connect DIS to Claude
The server address to paste into Claude settings:
https://dis--finereply3.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect DIS to ChatGPT
The server address to paste into ChatGPT settings:
https://dis--finereply3.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect DIS to Cursor
The server address to paste into Cursor settings:
https://dis--finereply3.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (25)
Raw names from tools/list. Only developers need these.
| compile_adl | Compile ADL through DIS V18. Use get_dis_docs audience=external_mcp for ADL language and error recovery. |
| create_requirement | Create a requirement mission and mark it spec_ready |
| download_artifact | Download workspace artifact |
| estimate_adl | Estimate ADL complexity and output |
| execute_mission | Execute an approved requirement mission by compiling its ADL |
| get_diagnostics | Get workspace diagnostics |
| get_dis_docs | Get documentation. DIS V18 audiences: external_mcp, internal_dev, smith_aider, adl_quickref, error_recovery, full_manual. Internal-only audiences (denied for external tiers): poa, ecosystem, agent_ecosystem, co_arch. |
| get_file | Read a workspace file or list a directory. Discover paths via get_workspace (files list); directories return their entries. Files larger than 512KB are rejected. |
| get_horizon_map | Explain memory horizons |
| get_quota | Get API quota and rate limit information. |
| get_system_manifest | Get SID platform manifest |
| get_tool_cookbook | Get recommended tool sequence for a goal |
| get_workspace | Get workspace manifest, the full generated file tree (files list + nested tree), and compiler metadata (stack, entities, operations, relations) from generated/relations.json. Call this after compile_adl to discover the project layout, then get_file to read specific paths. |
| list_issues | List reported issues by status (open/fixed/all). Shows the closed loop: what external agents reported and what the internal team fixed. |
| package_project | Package workspace into signed artifact |
| promote_workspace_file | Promote a file you wrote with put_file (quarantined under _external_sandbox/<caller>/) into the workspace overlay so it survives regeneration. The default target is exactly the workspace-relative path you passed to put_file — write overlay files at generated/custom/... for preservation (DIS copies generated/custom over the fresh tree). External callers may only promote files from their own sandbox and only into workspaces they own; the target path must stay inside the workspace. |
| put_file | Write a file into a workspace. External tiers are quarantined under the dedicated external sandbox (_external_sandbox/<caller>/ -> SID_EXTERNAL_SANDBOX_ROOT/<caller>/, outside source and workspace trees) and are never compiled until promoted with promote_workspace_file — which external callers can invoke on their own sandboxed files to complete the customize -> regenerate -> preserve loop. |
| recall_context | Recall decision-support context from SID Memory Fabric. Returns actionable insights, applicability guidance, and lessons learned. Use this before building any application. |
| report_issue | Report a platform issue to Memory Fabric for analysis. |
| report_outcome | Report mission outcome to Memory Fabric for evidence. |
| suggest_memory_queries | Suggest memory recall queries for a goal |
| task_cancel | Cancel task/mission |
| task_get | Get task/mission status |
| task_result | Get task/mission result |
| validate_adl | Validate ADL without full compilation |