Coding harnesses

A coding agent can reach the record through MCP tools, gateway model calls, or both. See Connect your agent for claude.ai, ChatGPT and Cursor.

Path	What the agent gets	What you configure
MCP door	Tools to read the record, propose entries and check authority before acting.	One MCP server entry.
Model door	Relevant cleared context added to model calls, with a receipt.	The harness’s base URL and headers.

Start with the MCP door if the agent needs the record as a tool. Add the model door to include relevant cleared context automatically.

Access

Syderial issues the MCP door address, the model door address and the credential to design partners. The examples use placeholders.

Connect the MCP door

The MCP door speaks the Model Context Protocol over streamable HTTP and follows standard MCP authorization. Your harness reads the door’s protected resource metadata, finds the authorization server and signs you in through your browser.

Claude Code

claude mcp add --transport http syderial https://YOUR-MCP-DOOR-ADDRESS/mcp

Start Claude Code, run /mcp, choose syderial and sign in. The session then lists the tools your credential allows.

Codex

~/.codex/config.toml

[mcp_servers.syderial]
url = "https://YOUR-MCP-DOOR-ADDRESS/mcp"

Then sign in:

codex mcp login syderial

A client that hasn’t signed in sees no tools. The MCP reference lists the tool families.

Send model calls through a door

Both harnesses can send model calls to another base URL with extra headers. Use the door address and credential headers from the Quickstart.

Claude Code

Claude Code calls the Anthropic messages API, so it uses the messages door.

export ANTHROPIC_BASE_URL="https://YOUR-DOOR-ADDRESS"
export ANTHROPIC_CUSTOM_HEADERS="$(cat syderial-headers.txt)"
export ANTHROPIC_AUTH_TOKEN="unused"   # the door reads the credential headers
export ANTHROPIC_MODEL="<a model alias>"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="<a model alias>"   # used for background calls
claude

ANTHROPIC_CUSTOM_HEADERS takes one Name: value pair per line, the same format as syderial-headers.txt. Setting ANTHROPIC_AUTH_TOKEN stops Claude Code from sending any other credential on your machine to the door.

Codex

Codex calls the OpenAI responses API, so it uses the responses door. Put each issued header value in an environment variable and map it in a provider entry.

~/.codex/config.toml

model = "<a model alias>"
model_provider = "syderial"

[model_providers.syderial]
name = "Syderial"
base_url = "https://YOUR-DOOR-ADDRESS/v1"
wire_api = "responses"

[model_providers.syderial.env_http_headers]
"<first header name issued to you>" = "SYDERIAL_CREDENTIAL_1"
"<second header name issued to you>" = "SYDERIAL_CREDENTIAL_2"

export SYDERIAL_CREDENTIAL_1="<first value issued to you>"
export SYDERIAL_CREDENTIAL_2="<second value issued to you>"
codex

Request fields

Each door’s contract covers the fields listed in the API reference for its protocol. Other request fields aren’t part of it. If your harness depends on one, call the model directly and connect the MCP door alone.

Capture hooks

Design partners also receive a hooks kit for Claude Code, Codex and OpenCode. It retains prompts and final turns as sources with their authors, and runs an advisory check before each tool call. Capturing a turn doesn’t post a journal entry. Your agent writes entries through the evidence-checked path. The kit includes its own setup notes.