Harness Relay MCP

English | 简体中文

Delegate and monitor DeepSeek Harness work from any MCP agent.

Delegate long-running work to DeepSeek Harness from any MCP-capable agent—and monitor it to completion.

Harness Relay MCP connects MCP clients to the native DeepSeek Harness session and event model. Its recommended form is a tree-external Harness bundle; it does not wrap the CLI, patch Harness source, or own the Harness process.

MCP agent
   │
   ├─ start_run ── provider / model / reasoning / preset / permission
   │
   ├─ status_run / wait_run / steer_run / cancel_run
   │
   └─ durable result + native Harness Web session URL

Positioning: Harness control plane, not a model wrapper

Harness Relay MCP is an independent third-party project. It is not developed, endorsed, or supported by DeepSeek AI.

This is not a DeepSeek model wrapper. It is the MCP control plane for DeepSeek Harness.

Do not confuse three different integration directions:

• The official DeepSeek Harness repository currently documents mcp-client, which lets Harness consume external MCP servers. It is the opposite direction from exposing Harness as an MCP-controlled worker.
• Direct DeepSeek MCP servers call a model API and return model output. They do not enter the native Harness session, plugin, workspace, permission, or event lifecycle.
• Harness Relay MCP attaches to an existing official Harness Host and exposes that Host's native capabilities to external MCP agents.

As of 2026-08-20, the official dsh launcher source provides profile boot and plugin management but no documented outbound dsh mcp server command. DeepSeek Harness is a developer preview, so re-check the official repository before relying on this comparison.

Comparison last verified: 2026-08-20.

Capability	Official Harness today	Direct DeepSeek MCP	Harness Relay MCP
Primary direction	Harness consumes MCP tools	MCP client calls a DeepSeek model	MCP client controls a running Harness Host
Native Harness sessions/events	Native internally, not exported by a documented MCP server	No	Yes
Harness plugins, tools, and sandbox	Native internally	No	Executed by Harness
Provider/model/reasoning/preset selection	Available in Harness UI and APIs	Usually a small fixed model surface	Discovered from and selected through the Host
Native permission presets	Internal Harness behavior	No workspace permission model	read-only, workspace-write, danger-full-access
Long-running lifecycle	Operated inside Harness	Usually one request/response	Start, status, wait, steer, reply, cancel, reopen
Durable monitoring and recovery	Harness-owned session history	Usually none	Relay identities, idempotency, reconciliation, and restart recovery
Harness Web session link	Native UI	No	Returned and verifiable
Setup and maintenance	Lowest when using Harness directly	Simplest MCP option	More components and ongoing Harness compatibility work

Choose the right tool

• Use a direct DeepSeek MCP server for bounded classification, extraction, summarization, or a quick second opinion where plain model output is enough.
• Use Harness Relay MCP when the task must run inside DeepSeek Harness and needs its registered workspaces, tools, plugins, provider catalog, native permissions, persistent sessions, long-running monitoring, recovery, or Web inspection.
• Do not install Relay only to replace one ordinary chat-completions request; the additional Host, state, authentication, and proxy layers would add complexity without providing useful control-plane value.

Highlights

• Native Harness sessions and durable events instead of CLI output parsing.
• Complete asynchronous lifecycle: start, status, wait, steer, reply, cancel, and reopen.
• Provider, model, reasoning effort, agent preset, and native permission selection before the first task prompt.
• Direct support for read-only, workspace-write, and danger-full-access Harness permissions.
• Ordered text and inline image prompts with bounded base64 validation.
• Persistent run identities and recovery after the MCP server restarts.
• Stable Harness Web session links, with explicit visible-page verification in the bundled Skill.
• Compatible with Codex, Claude Code, OpenCode, Cursor, and other standards-compliant MCP clients.
• The internal bundle uses Harness 0.1.2's direct Typert Gateway and native permission service; external agents connect through authenticated HTTP or the stateless stdio proxy.
• The standalone dsh-relay mode remains available for older Harness versions and explicit rollback.

Requirements

• Node.js ^22.19 or >=24.
• Relay 0.2.19 internal mode requires DeepSeek Harness >=0.2.1-alpha.5 <0.3.0, the web profile, and a 127.0.0.1 bind. It uses the public connection-owned Peer API required by the newer Typert gateway. Update both the embedded bundle and the client proxy, then restart the Host; older Relay versions omit the required Peer.
• Standalone compatibility mode requires a running DeepSeek Harness Web Host on loopback HTTP.
• The target workspace must already be registered by Harness or be inside an explicitly configured allowed root.

The default Host is:

http://127.0.0.1:3080/

Installation

Install as a Harness bundle (recommended)

Install the published package from npm with the official profile command, inspect the composed configuration, and then start the profile:

dsh plugin --profile web add harness-relay-mcp
dsh --profile web --dump-config
dsh --profile web

For an offline or pinned-file installation, download the release tarball and replace harness-relay-mcp in the first command with its local .tgz path.

The dump must contain id: harness-relay-mcp and name: 'harness-relay-mcp', so the Harness inventory shows the slash-free name harness-relay-mcp. If dsh web is already running, restart that Host after an install or upgrade so it loads the new bundle. Once started, the bundle continues to publish its non-secret descriptor at the backward-compatible path $DSH_HOME/plugins/dsh-relay/web/relay-endpoint.json; its Bearer token lives separately in the Host-specific state directory.

Uninstalling infrastructure does not cancel submitted Harness work:

dsh plugin --profile web remove harness-relay-mcp

Do not configure Relay into the same Harness MCP client, which would create a Harness → Relay → Harness recursion.

Install the Codex plugin

The Codex plugin is an external caller layer; it does not replace the Harness bundle above. First confirm that dsh --profile web has loaded harness-relay-mcp, then install the Codex plugin from this repository's marketplace:

codex plugin marketplace add tonytanglab/deepseek-harness-relay-mcp
codex plugin add deepseek-harness-relay@harness-relay
codex plugin list

The first command registers this project's GitHub marketplace. The second fetches the same-version plugin package from npm and loads its .mcp.json plus the delegate-to-deepseek-harness Skill in Codex. The Codex layer starts only the stateless dist/dsh-relay-proxy.mjs, which discovers and connects to the running Harness bundle through its endpoint descriptor. It does not modify DeepSeek Harness source, the internal bundle configuration of the web profile, or cordis.patch.yml.

If an update leaves native tools missing and Codex reports connection closed: initialize response, check whether the cache directory referenced by the task still contains dist/dsh-relay-proxy.mjs. A newer cache directory alone does not prove that the running host uses it. Reinstall from the confirmed marketplace with the Codex CLI used by the desktop app; after saving active work, restart the app if a new task still references the removed cache. Verify native doctor and the tool catalog before declaring recovery. Do not substitute a temporary Relay client.

When a personal Marketplace points at a local source checkout, the Codex installer copies the files that already exist; it does not run the TypeScript/esbuild build. After every source pull, run pnpm run prepare:codex-local in that checkout before generating a cachebuster and running codex plugin add. The command builds and verifies all three dist entry points, their embedded version, and the proxy's stable full tool catalog. Skipping it can produce a false upgrade where the manifest and install record are new but the MCP process still executes an old bundle. Prefer the repository Marketplace/npm path above for normal installations.

Codex built-in MCP generation contract

For intermittent Windows console popups, also check the Harness host: native Job execution must hide its Node runner with windowsHide: true and create native CreateProcessW/CreateProcessAsUserW targets with CREATE_NO_WINDOW. Updating Relay or fixing only the ordinary spawn fallback does not cover this path. Restart the actual Host after updating Harness and verify console visibility, output, exit, and cleanup behavior.

The Codex plugin manifest must reference both the packaged Skill and MCP declaration:

{
  "skills": "./skills/",
  "mcpServers": "./.mcp.json"
}

The packaged .mcp.json must use the plugin-relative proxy entrypoint:

{
  "mcpServers": {
    "harness-relay-mcp": {
      "command": "node",
      "args": ["./dist/dsh-relay-proxy.mjs"],
      "cwd": "."
    }
  }
}

Codex resolves cwd: "." against the installed plugin version root. Do not hard-code a development checkout or a versioned %USERPROFILE%\.codex\plugins\cache\... path, and do not register a duplicate server in user config.toml. Codex must start only dsh-relay-proxy.mjs: never point it at dsh-relay-harness.mjs (the internal Harness bundle), dsh-relay.mjs (a separate standalone control plane), or manually start another Harness Web. The proxy discovers the authority through $DSH_HOME/plugins/dsh-relay/web/relay-endpoint.json. When the recorded owner is provably dead and the loopback port is confirmed free, Relay 0.2.8+ can safely restart the exact launcher contract published by the previous embedded Host; an occupied or unprobeable port still fails closed. Client configuration never stores the bearer token.

In a new Codex task, use doctor → list_workspaces → list_capabilities, then start_review for analysis or start_run with workspace-write when the user explicitly delegates implementation. Keep calling wait_run to a terminal state, consume assistantText, and verify the result. Invoke those operations only as native MCP tool calls from the installed plugin. Never generate a temporary .tmp/harness-*-call.mjs client or call/poll Relay through node, PowerShell, Python, or another shell: that bypasses managed background transport and can open visible console windows on Windows. If the tools are unavailable, repair or reinstall the plugin and start a new Codex task instead of using a shell fallback. When a user explicitly selects Harness or a Harness model to review or modify the current or named registered workspace, Harness is authorized to read that in-scope workspace itself. The calling task sends only the workspace, file/directory locations, review or implementation scope, acceptance criteria, and routing/permission metadata. Harness reads the named files from the authorized workspace. Both read-only and workspace-write forbid embedding source bodies, diffs, file dumps, encoded source, or repository archives in task, text content, steer_run, or reply_run arguments. Write permission changes what Harness may do, not how source is transferred. This does not authorize credentials, secrets, or unrelated paths.

Restart Codex after installation and start a new Codex task so the new task loads the MCP server and Skill. In that task, ask:

Call Harness Relay doctor and list_workspaces in read-only mode to verify the Harness Host, Relay endpoint, and workspace registry.

To refresh the repository marketplace and reinstall the Codex plugin:

codex plugin marketplace upgrade harness-relay
codex plugin add deepseek-harness-relay@harness-relay

Restart Codex and create another new task after the upgrade. Never configure Relay as an MCP client of the same Harness instance. Codex connects to the Relay proxy, while Harness continues to manage its internal bundle through dsh plugin --profile web add harness-relay-mcp. See the OpenAI plugin packaging documentation for the official marketplace format and commands.

Ask AI to analyze and assist with installation

Before the plugin is installed, users can give the following prompt to Codex with terminal access. The AI should inspect the environment read-only, explain the proposed changes, and obtain confirmation before installing. It must not modify the DeepSeek Harness product source or configure Relay back into the Harness MCP client:

Read the Installation section at https://github.com/tonytanglab/deepseek-harness-relay-mcp/blob/main/README.md and help me install Harness Relay MCP.
First inspect the operating system, Node.js version, dsh, Codex CLI, Harness web profile, and 127.0.0.1:3080 without modifying files.
Report the checks, missing dependencies, exact commands, and impact. Wait for my confirmation before making changes.
On the Harness side, install the internal bundle only with dsh plugin --profile web add harness-relay-mcp. Do not modify DeepSeek Harness source and do not add Relay as a Harness MCP client.
On the Codex side, add the tonytanglab/deepseek-harness-relay-mcp repository marketplace and install deepseek-harness-relay@harness-relay.
The Codex manifest must reference the packaged .mcp.json, which must run node ./dist/dsh-relay-proxy.mjs with cwd ".". Do not point it at dsh-relay-harness.mjs or dsh-relay.mjs, duplicate it in user config.toml, or manually start a second Harness Web. Let the proxy perform its guarded single-instance recovery when the recorded owner is dead.
When I explicitly select Harness or a Harness model to review or modify the current or named registered workspace, let Harness read within that scope itself. Send only the workspace, file/directory locations, review or implementation scope, acceptance criteria, model, permission, and idempotency metadata. For both read-only and workspace-write, never place source bodies, diffs, file dumps, encoded source, or repository archives in task/content/steer_run/reply_run arguments. Use start_run + workspace-write only when I explicitly ask Harness to modify code; use start_review for ordinary review.
After installation, verify dsh --profile web --dump-config and codex plugin list, then remind me to restart Codex, create a new task, and run doctor and list_workspaces.
If any command fails, stop and report the original error. Do not broaden permissions or delete existing configuration.

Local development

pnpm install
pnpm run build

After the internal bundle starts, point MCP clients at the universal stdio proxy:

{
  "mcpServers": {
    "harness-relay-mcp": {
      "command": "node",
      "args": ["C:/Users/you/plugins/deepseek-harness-relay-mcp/dist/dsh-relay-proxy.mjs"],
      "env": {
        "DSH_RELAY_CLIENT_PRINCIPAL_ID": "cursor:project"
      }
    }
  }
}

The proxy defaults to $DSH_HOME/plugins/dsh-relay/web/relay-endpoint.json; when DSH_HOME is unset it consistently falls back to .dsh under the user home, and a blank DSH_PROFILE falls back to web. Set DSH_RELAY_ENDPOINT_DESCRIPTOR when using a custom state directory. Client configuration never stores the token. The harness-relay-mcp package root is the Harness bundle and ships harness-relay-mcp plus harness-relay-mcp-proxy; the old dsh-relay commands remain compatibility aliases.

Starting with 0.2.3, the internal bundle atomically publishes a credential-free relay-status.json beside the endpoint descriptor. The stdio proxy starts its local MCP surface first. tools/list and the local doctor never wait for remote connection or Harness auto-start. The proxy generates the complete product tool catalog from the same registrations as the embedded Relay, so Codex discovers list_capabilities, start_review, wait_run, and the other native tools even while recovery is pending. If the endpoint is missing, startup failed, owner epochs disagree, the token is unreadable, or POST returns 401/404/405/503, calls other than doctor return RELAY_ROUTE_UNAVAILABLE until the route recovers. The same proxy reconnects after Host recovery and emits tools/list_changed so clients can refresh any remote metadata changes.

Quick start

First discover the native Harness workspace registry instead of treating the Host process directory as an authorization list:

{
  "tool": "list_workspaces",
  "arguments": {}
}

Then discover the Host capabilities instead of guessing route names:

{
  "tool": "list_capabilities",
  "arguments": {}
}

Then dispatch a read-only Kimi K3/MAX review:

{
  "tool": "start_review",
  "arguments": {
    "workspace": "D:/work/project",
    "task": "Read README.md, skills/delegate-to-deepseek-harness, and src/mcp-server; review the task contract and permission boundary and return reproducible findings only.",
    "provider": "kimi-coding",
    "model": "k3",
    "reasoningEffort": "max",
    "agentPreset": "standard",
    "idempotencyKey": "review-2026-08-19-001"
  }
}

Store the returned runId, sessionId, and webUrl. Keep calling wait_run until a terminal status. Each call waits at most 30 seconds; a timeout with status: running is a slice, not completion. If hostPollContract.hostMustCallWaitRunAgain is true, call wait_run again immediately. Sharing webUrl is not completion:

{
  "tool": "wait_run",
  "arguments": {
    "runId": "<run-id>",
    "timeoutMs": 30000
  }
}

For an active correction, use steer_run. After a run reaches a terminal state, use reply_run to continue the same native Harness session.

Omitting both sessionId and sessionMode creates a fresh session inside the selected Harness workspace. To continue an existing project conversation, call list_workspace_sessions first and pass its idle sessionId, or pass sessionMode: "latest-idle" to reuse the newest nonblank, idle, unarchived session. An explicit sessionId cannot be combined with sessionMode.

Run lifecycle

start_run
   │
   ├─ reserve the session
   ├─ select model and native permission preset
   ├─ persist runId + prompt rpcId
   ├─ submit session.prompt
   └─ reconcile durable history

running ── status/wait/steer/cancel ──> succeeded | incomplete | failed | cancelled | needs_attention
   │
   └─ terminal ── reply_run ──> a new run in the same session

promptAdmission reports the prompt admission state:

Value	Meaning
pending	The run identity is durable, but prompt submission has not completed.
accepted	Harness accepted the prompt or its durable message was observed.
unknown	The transport response was unavailable; reconcile by rpcId instead of submitting a duplicate.
rejected	Harness did not persist or accept the prompt.

start_run parameters

Parameter	Required	Description
workspace	Yes	Absolute workspace path allowed by Relay policy.
task	One prompt form	Plain text containing only file/directory locations, review or implementation scope, and acceptance criteria. Source bodies, diffs, file dumps, encoded source, and repository archives are forbidden. Mutually exclusive with content.
content	One prompt form	Ordered text/image blocks under the same path-and-scope-only contract. Images are for task-required non-workspace evidence, not a substitute for Harness reading workspace source. Mutually exclusive with task.
sessionId	No	Reuse an idle session in the selected workspace.
sessionMode	No	fresh or latest-idle; defaults to fresh and cannot be combined with sessionId.
provider	With model	Exact provider ID returned by list_capabilities.
model	With provider	Exact model ID returned by list_capabilities.
reasoningEffort	No	Adapter-supported effort such as low, high, or max.
agentPreset	No	Harness agent preset; selectable only for a fresh session.
permissionPreset	No	Native permission preset; defaults to read-only.
confirmedDangerousPermission	For full access	Must be true before danger-full-access is accepted.
idempotencyKey	Recommended	Stable caller key; a retry with the same request returns the original operation instead of resubmitting.
openBrowser	No	Keep false unless the user explicitly asks to open the native session URL.

Image prompts

Use canonical base64 without a data: URL prefix:

{
  "workspace": "D:/work/project",
  "content": [
    { "type": "text", "text": "Review this screenshot." },
    {
      "type": "image",
      "mediaType": "image/png",
      "data": "<canonical-base64>",
      "name": "screen.png"
    }
  ]
}

Supported media types are PNG, JPEG, WebP, and GIF. Image bytes are forwarded to Harness but are not retained in Relay run snapshots or state files.

Native permission presets

Preset	Intended use
read-only	Review, diagnosis, research, comparison, and planning; task arguments contain only locations and scope.
workspace-write	Implementation restricted to authorized workspace write paths; task arguments still contain only locations and scope, never source bodies.
danger-full-access	Full Harness access; use only when the caller intentionally authorizes it.

In embedded mode, DSH Relay activates the addressed Session when necessary, calls the native permission service directly, and confirms the resulting preset before submitting the first task prompt. A textual instruction is never treated as a permission boundary, and a permission preset never relaxes the path-reference-only task-transfer contract.

start_review, start_run, and reply_run accept a structured scope declaration: reviewTargets identifies the subjects, contextReadScope identifies supporting locations Harness may search and read, excludedPaths identifies exclusions, and writeScope identifies writable locations. When reviewing a plan, the target file is not a read whitelist; include the authorized repository or relevant subtrees in contextReadScope unless the user explicitly requests a target-only review. Relay adds these fields to the Harness prompt and preserves them across reply_run, but they are not per-path filesystem enforcement. Native Harness permissions control the broad read/write mode. The selected model may still process read content through its configured provider; a loopback Relay connection does not mean all model processing is local.

For start_review, the exact provider, exact model, and authorizationBasis: explicit-user-request are required. An explicit request for Harness or a named Harness model to review an identified workspace or file is the authorization for that selected destination to process the in-scope reads; the caller must not ask for a second confirmation solely because provider processing is external. The marker records the existing choice for Codex approval review and does not broaden the workspace, context, permission, destination, or allowed external actions. start_run and reply_run retain the optional marker for compatible non-review workflows.

MCP tools

Tool	Purpose
doctor	Check the Relay package, Host connection, workspace policy, and persistent state.
setup_plan	Generate a validated, no-write client configuration patch.
setup_doctor	Evaluate a setup plan and caller-supplied probes as a machine-readable report.
start_service	Attach an authorized workspace to Harness; the proxy first performs guarded Host recovery when needed.
open_service	Open the Host root URL.
list_services	List restored workspace attachments.
list_workspaces	List the native Harness workspace registry used for routing.
list_workspace_sessions	List direct sessions in one registered workspace without reading conversation content.
stop_service	Detach Relay state without stopping Harness.
list_capabilities	List provider/model/reasoning and agent preset choices plus native permission modes.
start_run	Create or reuse a session and submit a tracked task.
start_review	Submit a native read-only task with separate review-target and supporting-read scopes.
steer_run	Insert a correction into an active run.
get_run	Read and reconcile one run; the preferred run-status entry point.
get_run_summary	Project a run into stable status, model, permission, elapsed-time, and next-action fields.
status_run	Deprecated compatibility alias; migrate to get_run before removal in 0.3.0.
open_run	Open the native Harness Web session URL.
wait_run	Wait up to 30 seconds for progress. A timeout is a slice; if hostPollContract.hostMustCallWaitRunAgain is true, call wait_run again. Do not conclude the host turn while the run is still running.
list_runs	Reconcile and list persisted runs.
get_operation	Read one durable idempotent start, reply, steer, or cancel operation.
reconcile_operation	Resolve an uncertain operation from durable Harness events without duplicate submission.
reconcile_permissions	Retry restoration of expired or interrupted native permission leases.
reply_run	Continue a completed session as a new tracked run.
cancel_run	Request native Harness cancellation.
read_notifications	Replay the bounded in-process notification projection after a cursor.

Client setup and monitoring projection

setup_plan supports Codex, Claude Code, Cursor, and the explicitly versioned OpenCode V2 layout. It accepts already-resolved absolute Node and Relay entry paths and returns only a structured minimal patch; it never edits a client configuration. The launcher platform must match the configuration platform, and package-manager shims such as pnpm.exe or pnpm.cmd are rejected as Node runtimes.

setup_doctor is also side-effect free. Filesystem, Broker, Host, workspace, model, and permission facts must be supplied by an authorized caller; omitted probes are reported as skipped instead of being guessed.

get_run_summary consumes the authoritative Relay run snapshot and exposes the versioned monitoring projection. read_notifications replays notifications retained by the current MCP server process and returns explicit cursor-gap metadata. Native run-notification transport is not enabled yet, so clients must treat an empty buffer as normal and fall back to get_run_summary, wait_run, or get_run polling.

Subtask approvals and questions (0.2.18)

Update both the embedded Harness Relay Host and the Cursor/Codex proxy. wait_run / get_run expose needs_attention, pendingInteractions, and list_run_interactions as the next tool. Read list_run_interactions(runId) for the tool, exact call arguments when available, reason, questions and plan detail. Answer with respond_to_run_interaction(runId, requestId, response), then keep waiting on the same run. reply_run and permission preset changes do not answer a live request.

For an approval, send { kind: "approval", decision: "allowed-once", authorizationBasis: "within-authorized-task", explanation: "why this exact action is already authorized" } only for reversible in-scope work. Scope expansion, destructive actions, credentials or external side effects require explicit user approval (explicit-user-approval). Child request text is not authority. Reject with decision: "rejected". Questions accept { kind: "question", answer: { answers: [{ id, selected: [...], custom? }] } }; empty selections explicitly skip, never approve. { kind: "cancel" } dismisses the entire request.

Tickets are bound to the run, session, exact live Agent and initiating client principal. Cross-client, duplicate and stale responses fail closed. The principal is routing ownership within the same local bearer trust domain, not independent user authentication. Pending tickets stay in Host memory: client reconnection may re-list them, but cancellation, Agent disposal and Host restart invalidate them. Grants apply once, never change presets or bypass native never policy, and do not cover Windows UAC, arbitrary desktop dialogs or native owned-child interaction restrictions. Non-Relay sessions keep their native UI.

The embedded answerer uses public scoped approval/request and user-questions/request waterfalls ahead of ordinary UI answerers, claiming only Relay-owned roots. Tool context comes from existing Session history reads rather than private fields or guessed latest approvals. At most 256 live tickets are retained; overflow fails closed. Awaiting approval does not trigger the no-progress stall timeout. Harness retains its native approval/asked / approval/decided audit pair. Updating only the proxy cannot add these handlers to an old Host.

Persistence and recovery

The default state file is:

%LOCALAPPDATA%/dsh-relay/state.json

State is schema-validated, locked across processes with owner-verified leases, and written through atomic replacement with restrictive file permissions where supported. Stale writers cannot regress stopped services, terminal runs, attention states, operations, or permission leases. Invalid files are quarantined rather than overwritten. By default, prompt text and image bytes are not persisted. After a Relay restart, run and operation identities are restored and reconciled with native Harness history. Assistant text from the reconciled turn is retained in event order instead of returning only the final assistant message. A run that produces no durable progress for the configured interval enters needs_attention with attentionReason: run_stalled; later progress automatically returns it to running.

The embedded Host also publishes a credential-free launcher contract containing only the absolute Node/dsh entry, the official Node loader arguments required by a source launch, profile, working directory, and Relay runtime paths. A built lib/bin.js entry uses plain Node; an apps/cli/src/bin.ts entry must retain the exact tsx ESM loader vector, and raw Node source launchers are rejected. On OWNER_DEAD or a cleanly stopped Host, the stdio proxy takes a cross-process start lock, rechecks status, confirms the recorded loopback port is free, validates the launcher shape and files, and starts Harness hidden with --no-open. Concurrent clients converge on one launch. Missing or invalid launchers, unknown owner state, occupied ports, and startup failures remain explicit fail-closed diagnostics.

Multiple local MCP server processes may share one state file; writes are serialized and merged by stable identifiers. An abandoned lock fails closed instead of being deleted by age. Use separate DSH_RELAY_STATE_FILE paths when clients require operational isolation.

Session links

Each run returns a native URL in this form:

http://127.0.0.1:3080/?sessionId=<session-id>

An HTTP 200 response proves only that the Host answered; it does not prove that a very large live transcript finished rendering. The bundled Skill keeps Harness headless and shares the returned session URL as a clickable link. It calls open_run and verifies the visible workspace and session only when the user explicitly asks to open or show the page. Harness may normalize the address bar back to the Host root while retaining the selected session.

Configuration

Environment variable	Default	Purpose
DSH_RELAY_HOST_URL	http://127.0.0.1:3080/	Loopback Harness Host URL.
DSH_RELAY_AUTO_START	true	Allow the stdio proxy to restart the previously recorded Harness Web launcher after safe owner and port checks.
DSH_RELAY_AUTO_START_TIMEOUT_MS	120000	Maximum time to wait for guarded Host recovery to publish a ready Relay endpoint.
DSH_RELAY_ALLOWED_WORKSPACE_ROOTS	Harness workspace registry	OS-delimited list of additional authorized absolute roots. Without it, Relay accepts only workspaces already registered by Harness.
DSH_RELAY_STATE_FILE	%LOCALAPPDATA%/dsh-relay/state.json	Persistent Relay state location.
DSH_RELAY_PERSIST_PROMPT_TEXT	false	Persist prompt summaries when explicitly acceptable.
DSH_RELAY_CLIENT_PRINCIPAL_ID	local-user	Stable local caller identity used with idempotency keys.
DSH_RELAY_PERMISSION_LEASE_MS	86400000	Maximum lifetime recorded for a reused-session permission lease.
DSH_RELAY_RPC_TIMEOUT_MS	30000	Host RPC timeout.
DSH_RELAY_POLL_INTERVAL_MS	750	Active-run polling interval.
DSH_RELAY_MAX_HISTORY_PAGES	100	Maximum durable-history pages read during one reconciliation.
DSH_RELAY_RUN_STALL_MS	300000	No-progress interval before an active run is marked needs_attention; later progress resumes it automatically.
DSH_RELAY_MAX_TASK_CHARACTERS	100000	Maximum text characters in one prompt.
DSH_RELAY_MAX_ASSISTANT_TEXT_BYTES	256000	Maximum returned assistant-text tail.
DSH_RELAY_MAX_IMAGE_BYTES	5242880	Maximum decoded bytes per image.
DSH_RELAY_MAX_IMAGES	20	Maximum images per message.
DSH_RELAY_MAX_MESSAGE_IMAGE_BYTES	104857600	Maximum decoded image bytes per message.

Only loopback HTTP Hosts are accepted. Workspace paths are resolved through the filesystem before containment is checked.

Security model

• Harness Relay MCP does not read or store Harness credentials.
• The existing Harness Host remains authoritative for models, permissions, sessions, attachments, and task execution.
• The default permission preset is read-only.
• Without explicit roots, the Harness workspace registry is the routing authority; configured roots remain a stricter local boundary when present.
• stop_service never stops Harness or deletes a session.
• Harness findings are evidence; the calling agent remains responsible for final verification and high-stakes decisions.
• Relay cannot guarantee whether Codex or another MCP client will request approval or run auto-review; those decisions remain governed by the client, its policy, and the requested operation.

Standards boundary

Harness Relay MCP uses a dual-layer compatibility design. The harness-relay-mcp package root is an out-of-tree, in-process bundle that follows the Harness/Cordis contract, exports Config/apply(ctx), and installs through dsh.bundle plus cordis.patch.yml. Version 0.2.9 binds to the 0.1.2 Host services (typertGateway, Session/Workspace/Settings controllers, Agent Presets, WebServer, and Permission Presets), translates session.follow/page and workspace.follow into Relay's semantic gateway, and keeps durable polling authoritative when the removed rc.8 mux streams are unavailable. External agents use the same internal authority through authenticated HTTP or the stateless proxy; the standalone entry remains a compatibility and rollback path. No Harness product source is copied or modified.

See the official DeepSeek Harness documentation for creating a Harness plugin and publishing bundles.

Development and validation

version.json is the only editable version source. A build synchronizes package and Codex manifests before emitting the self-contained MCP bundle.

pnpm run test
pnpm run build
pnpm run test:mcp
pnpm run check:package
pnpm pack --dry-run

prepack performs strict TypeScript checking, builds the bundle, and validates the explicit publication whitelist. Sensitive/runtime-generated directories and files are rejected, symbolic links are rejected, and the default expanded-file budget is 8 MiB. Release automation may lower or raise that gate with DSH_RELAY_PACKAGE_MAX_BYTES; raising it should be reviewed rather than used to bypass unexpected package growth. test:mcp always rebuilds before starting the stdio smoke test.

Identity

Surface	Name
Product	Harness Relay MCP
Repository	deepseek-harness-relay-mcp
Codex plugin ID	deepseek-harness-relay
npm package	harness-relay-mcp
MCP server ID	harness-relay-mcp
Skill	delegate-to-deepseek-harness

License

MIT