| summary | Expose OpenClaw channel conversations over MCP and manage saved MCP server definitions | |||
|---|---|---|---|---|
| read_when |
|
|||
| title | MCP | |||
| sidebarTitle | MCP |
openclaw mcp has two jobs:
- run OpenClaw as an MCP server with
openclaw mcp serve - manage OpenClaw-managed outbound MCP server definitions with
list,show,status,doctor,probe,add,set,configure,tools,login,logout,reload, andunset
serve is OpenClaw acting as an MCP server. The other subcommands are OpenClaw acting as an MCP client-side registry for servers its own runtimes may consume later.
Use openclaw acp when OpenClaw should host a coding harness session itself and route that runtime through ACP.
| Goal | Use | Why |
|---|---|---|
| Let an external MCP client read/send OpenClaw channel conversations | openclaw mcp serve |
OpenClaw is the MCP server and exposes Gateway-backed conversations over stdio. |
| Save third-party MCP servers for OpenClaw-managed agent runs | openclaw mcp add, set, configure, tools, login |
OpenClaw is the MCP client-side registry and later projects those servers into eligible runtimes. |
| Check a saved server without running an agent turn | openclaw mcp status, doctor, probe |
status and doctor inspect config; probe opens a live MCP connection and lists capabilities. |
| Edit MCP config from a browser | Control UI /settings/mcp (/mcp alias) |
The page shows inventory, enablement, OAuth/filter summaries, command hints, and a scoped mcp editor. |
| Give Codex app-server a scoped native MCP server | mcp.servers.<name>.codex |
The codex block only affects Codex app-server thread projection and is stripped before native config handoff. |
| Run ACP-hosted harness sessions | openclaw acp and ACP Agents |
ACP bridge mode does not accept per-session MCP server injection; configure gateway/plugin bridges instead. |
This is the openclaw mcp serve path.
Use openclaw mcp serve when:
- Codex, Claude Code, or another MCP client should talk directly to OpenClaw-backed channel conversations
- you already have a local or remote OpenClaw Gateway with routed sessions
- you want one MCP server that works across OpenClaw's channel backends instead of running separate per-channel bridges
Use openclaw acp instead when OpenClaw should host the coding runtime itself and keep the agent session inside OpenClaw.
openclaw mcp serve starts a stdio MCP server. The MCP client owns that process. While the client keeps the stdio session open, the bridge connects to a local or remote OpenClaw Gateway over WebSocket and exposes routed channel conversations over MCP.
The bridge uses existing Gateway session route metadata to expose channel-backed conversations. A conversation appears when OpenClaw already has session state with a known route such as:
channel- recipient or destination metadata
- optional
accountId - optional
threadId
This gives MCP clients one place to:
- list recent routed conversations
- read recent transcript history
- wait for new inbound events
- send a reply back through the same route
- see approval requests that arrive while the bridge is connected
Filters: `limit` (max 500), `search`, `channel`, `includeDerivedTitles`, `includeLastMessage`.
Use this when a generic MCP client needs near-real-time delivery without a Claude-specific push protocol.
Current behavior:
- requires an existing conversation route
- uses the session's channel, recipient, account id, and thread id
- sends text only
- `allow-once`
- `allow-always`
- `deny`
The bridge keeps an in-memory event queue while it is connected.
Current event types:
messageexec_approval_requestedexec_approval_resolvedplugin_approval_requestedplugin_approval_resolvedclaude_permission_request
The bridge can also expose Claude-specific channel notifications. This is the OpenClaw equivalent of a Claude Code channel adapter: standard MCP tools remain available, but live inbound messages can also arrive as Claude-specific MCP notifications.
`--claude-channel-mode off`: standard MCP tools only. `--claude-channel-mode on`: enable Claude channel notifications. `--claude-channel-mode auto`: current default; same bridge behavior as `on`.When Claude channel mode is enabled, the server advertises Claude experimental capabilities and can emit:
notifications/claude/channelnotifications/claude/channel/permission
Current bridge behavior:
- inbound
usertranscript messages are forwarded asnotifications/claude/channel - Claude permission requests received over MCP are tracked in-memory
- if the command owner in the linked conversation later sends
yes <id>orno <id>(<id>is the 5-letter request id, excludingl), the bridge converts that tonotifications/claude/channel/permission - these notifications are live-session only; if the MCP client disconnects, there is no push target
This is intentionally client-specific. Generic MCP clients should rely on the standard polling tools.
Example stdio client config:
{
"mcpServers": {
"openclaw": {
"command": "openclaw",
"args": [
"mcp",
"serve",
"--url",
"wss://gateway-host:18789",
"--token-file",
"/path/to/gateway.token"
]
}
}
}For most generic MCP clients, start with the standard tool surface and ignore Claude mode. Turn Claude mode on only for clients that actually understand the Claude-specific notification methods.
openclaw mcp serve supports:
The bridge does not invent routing. It only exposes conversations that Gateway already knows how to route.
That means:
- sender allowlists, pairing, and channel-level trust still belong to the underlying OpenClaw channel configuration
messages_sendcan only reply through an existing stored route- approval state is live/in-memory only for the current bridge session
- bridge auth should use the same Gateway token or password controls you would trust for any other remote Gateway client
If a conversation is missing from conversations_list, the usual cause is not MCP configuration. It is missing or incomplete route metadata in the underlying Gateway session.
OpenClaw ships a deterministic Docker smoke for this bridge:
pnpm test:docker:mcp-channelsThat smoke runs a single container: it seeds conversation state, starts the Gateway, then spawns openclaw mcp serve as a stdio child process and drives it as an MCP client. It verifies conversation discovery, transcript reads, attachment metadata reads, live event queue behavior, and Claude-style channel and permission notifications over the real stdio MCP bridge. Outbound send routing (messages_send reusing the stored conversation route) is covered separately by unit tests in src/mcp/channel-server.test.ts.
This is the fastest way to prove the bridge works without wiring a real Telegram, Discord, or iMessage account into the test run.
For broader testing context, see Testing.
Usually means the Gateway session is not already routable. Confirm that the underlying session has stored channel/provider, recipient, and optional account/thread route metadata. Expected. The live queue starts when the bridge connects. Read older transcript history with `messages_read`. Check all of these:- the client kept the stdio MCP session open
- `--claude-channel-mode` is `on` or `auto`
- the client actually understands the Claude-specific notification methods
- the inbound message happened after the bridge connected
This is the openclaw mcp list, show, status, doctor, probe, add, set,
configure, tools, login, logout, reload, and unset path.
These commands do not expose OpenClaw over MCP. They manage OpenClaw-managed MCP server definitions under mcp.servers in OpenClaw config. They do not read mcporter servers from config/mcporter.json.
Those saved definitions are for runtimes that OpenClaw launches or configures later, such as embedded OpenClaw and other runtime adapters. OpenClaw stores the definitions centrally so those runtimes do not need to keep their own duplicate MCP server lists.
- these commands only read or write OpenClaw config - `status`, `list`, `show`, `doctor` without `--probe`, `set`, `configure`, `tools`, `logout`, `reload`, and `unset` do not connect to the target MCP server - `login` performs the MCP OAuth network flow for the configured HTTP server and saves the resulting local credentials - `status --verbose` prints resolved transport, auth, timeout, filter, and parallel-tool-call hints without connecting - `doctor` checks saved definitions for local setup problems such as missing stdio commands, invalid working directories, missing TLS files, disabled servers, literal sensitive header/env values, and incomplete OAuth authorization - `doctor --probe` adds the same live connection proof as `probe` after static checks pass - `probe` connects to the selected server or all configured servers, lists tools, and reports capabilities/diagnostics - `add` builds a definition from flags and probes before saving unless `--no-probe` is set or OAuth authorization is needed first - runtime adapters decide which transport shapes they actually support at execution time - `enabled: false` keeps a server saved but excludes it from embedded runtime discovery - `requestTimeoutMs` and `connectionTimeoutMs` set per-server request and connection timeouts in milliseconds - `supportsParallelToolCalls: true` marks servers that adapters can call concurrently - HTTP servers can use static headers, OAuth login, TLS verification control, and mTLS certificate/key paths - embedded OpenClaw exposes configured MCP tools in normal `coding` and `messaging` tool profiles; `minimal` still hides them, and `tools.deny: ["bundle-mcp"]` disables them explicitly - per-server `toolFilter.include` and `toolFilter.exclude` filter discovered MCP tools before they become OpenClaw tools - servers that advertise resources or prompts also expose utility tools for listing/reading resources and listing/fetching prompts; those generated utility names (`resources_list`, `resources_read`, `prompts_list`, `prompts_get`) use the same include/exclude filter - dynamic MCP tool-list changes invalidate the cached catalog for that session; the next discovery/use refreshes from the server - repeated MCP tool request/protocol failures pause that server briefly so one broken server does not consume the whole turn - session-scoped bundled MCP runtimes are reaped after 10 minutes of idle time and one-shot embedded runs clean them up at run endRuntime adapters may normalize this shared registry into the shape their downstream client expects. For example, embedded OpenClaw consumes OpenClaw transport values directly, while Claude Code and Gemini receive CLI-native type values such as http, sse, or stdio.
Codex app-server also honors an optional codex block on each server. This is
OpenClaw projection metadata for Codex app-server threads only; it does not
change ACP sessions, generic Codex harness config, or other runtime adapters.
Use non-empty codex.agents to project a server only into specific OpenClaw
agent ids. Empty, blank, or invalid agent lists are rejected by config
validation and omitted by the runtime projection path instead of becoming
global. Use codex.defaultToolsApprovalMode (auto, prompt, or approve)
to emit Codex's native default_tools_approval_mode for a trusted server.
OpenClaw strips the codex metadata before handing the native mcp_servers
config to Codex.
Commands:
openclaw mcp listopenclaw mcp show [name]openclaw mcp status [--verbose]openclaw mcp doctor [name] [--probe]openclaw mcp probe [name]openclaw mcp add <name> [flags]openclaw mcp set <name> <json>openclaw mcp configure <name> [flags]openclaw mcp tools <name> [--include csv] [--exclude csv] [--clear]openclaw mcp login <name> [--code code]openclaw mcp logout <name>openclaw mcp reloadopenclaw mcp unset <name>
Notes:
listsorts server names.showwithout a name prints the full configured MCP server object.statusclassifies configured transports without connecting.--verboseincludes resolved launch, timeout, OAuth, filter, and parallel-call details, including when stored OAuth tokens require additional authorization. Credential-bearing stdio arguments are redacted in text and JSON output.doctorperforms static checks without connecting. Add--probewhen the command should also verify that enabled servers connect.probeconnects and reports tool counts, resources/prompts support, list-change support, and diagnostics.addaccepts stdio flags such as--command,--arg,--env, and--cwd, or HTTP flags such as--url,--transport,--header,--auth oauth, TLS, timeout, and tool-selection flags.setexpects one JSON object value on the command line.configureupdates enablement, tool filters, timeouts, OAuth, TLS, and parallel-tool-call hints without replacing the whole server definition. Add--probeto verify the updated server before saving.toolsupdates per-server tool filters. Include/exclude entries are MCP tool names and simple*globs.loginruns the OAuth flow for HTTP servers configured withauth: "oauth". The first run prints an authorization URL; rerun with--codeafter approval.logoutclears stored OAuth credentials for the named server without removing the saved server definition.reloaddisposes cached in-process MCP runtimes for the current CLI process only. Gateway or agent processes in another process still need their own reload or restart path.- Use
transport: "streamable-http"for Streamable HTTP MCP servers.openclaw mcp setalso normalizes CLI-nativetype: "http"to the same canonical config shape for compatibility. unsetfails if the named server does not exist.
Examples:
openclaw mcp list
openclaw mcp show context7 --json
openclaw mcp status --verbose
openclaw mcp doctor --probe
openclaw mcp probe context7 --json
openclaw mcp add memory --command npx --arg -y --arg @modelcontextprotocol/server-memory
openclaw mcp set context7 '{"command":"uvx","args":["context7-mcp"]}'
openclaw mcp tools context7 --include 'resolve-library-id,get-library-docs'
openclaw mcp set docs '{"url":"https://mcp.example.com","transport":"streamable-http"}'
openclaw mcp configure docs --timeout 20 --connect-timeout 5 --include 'search,read_*'
openclaw mcp configure docs --auth oauth --oauth-scope 'docs.read'
openclaw mcp login docs
openclaw mcp logout docs
openclaw mcp unset context7These examples save server definitions only. Run openclaw mcp doctor --probe afterward to prove that the server starts and exposes tools.
Scope filesystem servers to the smallest directory tree that the agent should read or edit.
Use a tool filter if the server exposes write tools that should not be available to normal agents.
`doctor` checks that `cwd` exists and that the command resolves from the configured environment.
Use OAuth when the remote server supports it. If the server requires static headers, avoid committing literal bearer tokens.
Direct desktop-control servers inherit the permissions of the process they launch. Use narrow tool filters and OS-level permission prompts.
Use --json for scripts and dashboards. Field sets can grow over time, so consumers should ignore unknown keys.
`doctor --json` exits nonzero when any enabled checked server has an `error`-level issue. `warning` and `info` issues are reported but do not make the command fail by themselves.
`probe --json` opens a live MCP client session and prints its result directly; unlike `status`/`doctor`, the output has no top-level `path` field. `resources` and `prompts` keys are present only when the server actually advertises that capability (a server without prompts omits the `prompts` key rather than reporting `false`). Use `probe` for reachability and capability proof, not for static config audits.
Example config shape:
{
"mcp": {
"servers": {
"context7": {
"command": "uvx",
"args": ["context7-mcp"]
},
"docs": {
"url": "https://mcp.example.com",
"transport": "streamable-http",
"requestTimeoutMs": 20000,
"connectionTimeoutMs": 5000,
"supportsParallelToolCalls": true,
"auth": "oauth",
"oauth": {
"scope": "docs.read"
},
"sslVerify": true,
"clientCert": "/path/to/client.crt",
"clientKey": "/path/to/client.key",
"toolFilter": {
"include": ["search_*"],
"exclude": ["admin_*"]
}
}
}
}
}Launches a local child process and communicates over stdin/stdout.
| Field | Description |
|---|---|
command |
Executable to spawn (required) |
args |
Array of command-line arguments |
env |
Extra environment variables |
cwd / workingDirectory |
Working directory for the process |
OpenClaw rejects interpreter-startup, loader-hijack, and shell-init env keys before spawning a stdio MCP server, even if they appear in a server's env block. This uses the same host environment security policy as other OpenClaw-spawned processes: it blocks known interpreter startup hooks (for example NODE_OPTIONS, PYTHONSTARTUP, PERL5OPT, RUBYOPT, BASHOPTS, KSH_ENV), shared-library and function-injection prefixes (DYLD_*, LD_*, BASH_FUNC_*), and similar runtime-control variables. Startup drops these silently and logs a warning so they cannot inject an implicit prelude, swap the interpreter, enable a debugger, or hijack the dynamic linker against the stdio process. An explicit allowlist keeps ordinary MCP credential env vars usable (GITHUB_TOKEN, GH_TOKEN, GITLAB_TOKEN, NPM_TOKEN, NODE_AUTH_TOKEN, DATABASE_URL, MONGODB_URI, REDIS_URL, AMQP_URL, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN, AZURE_CLIENT_ID, AZURE_CLIENT_SECRET), along with ordinary proxy and server-specific env vars (HTTP_PROXY, custom *_API_KEY, etc.). Other AWS_* keys such as AWS_CONFIG_FILE and AWS_SHARED_CREDENTIALS_FILE remain blocked because they point at credential files rather than carry a credential value directly.
If your MCP server genuinely needs one of the blocked variables, set it on the gateway host process instead of under the stdio server's env.
Connects to a remote MCP server over HTTP Server-Sent Events.
| Field | Description |
|---|---|
url |
HTTP or HTTPS URL of the remote server (required) |
headers |
Optional key-value map of HTTP headers (for example auth tokens) |
connectionTimeoutMs |
Per-server connection timeout in ms (optional) |
requestTimeoutMs |
Per-server MCP request timeout in milliseconds |
auth: "oauth" |
Use MCP OAuth credentials saved by openclaw mcp login |
sslVerify |
Set false only for explicitly trusted private HTTPS endpoints |
clientCert / clientKey |
mTLS client certificate and key paths |
supportsParallelToolCalls |
Hint that concurrent calls are safe for this server |
Example:
{
"mcp": {
"servers": {
"remote-tools": {
"url": "https://mcp.example.com",
"auth": "oauth",
"requestTimeoutMs": 20000,
"headers": {
"Authorization": "Bearer <token>"
}
}
}
}
}Sensitive values in url (userinfo) and headers are redacted in logs and status output. openclaw mcp doctor warns when sensitive-looking headers or env entries contain literal values, so operators can move those values out of committed config.
OAuth is for HTTP MCP servers that advertise the MCP OAuth flow. Static Authorization headers are ignored for a server while auth: "oauth" is enabled. Credentials saved by openclaw mcp login work with embedded MCP, CLI runners, and the local Codex app-server.
Native MCP OAuth sessions live in the owner-only shared SQLite database at <state-dir>/state/openclaw.sqlite (mcp_oauth_stores). The row can contain access and refresh tokens, dynamic client registration secrets, discovery metadata, and the temporary PKCE verifier. Refresh, login, and logout use the same SQLite lease, so parallel OpenClaw processes cannot consume one refresh token or resurrect a logged-out session.
Upgrades from the retired <state-dir>/mcp-oauth/*.json store are handled only by openclaw doctor --fix. Runtime code never reads, writes, or falls back to those files.
Until credentials are available, OpenClaw omits only that MCP server from the agent runtime instead of failing the agent turn. The operator, or an agent with shell access, can then run openclaw mcp login <name> and use the server on a later turn.
If a server rejects a token with insufficient_scope, OpenClaw preserves the requested scope and asks for openclaw mcp login <name> instead of repeating a refresh that cannot grant new scope. That login starts a new authorization request while keeping the previous token until replacement credentials are saved.
When a remote MCP service is already backed by a separate OpenClaw refresh-capable auth profile, you can optionally set oauth.authProfileId. OpenClaw refreshes either credential source before runtime projection and passes only the current access token to the downstream MCP client.
```bash
openclaw mcp set docs '{"url":"https://mcp.example.com/mcp","transport":"streamable-http","auth":"oauth","oauth":{"scope":"docs.read"}}'
```
For an auth-profile-backed bearer, save the profile binding:
```bash
openclaw mcp set docs '{"url":"https://mcp.example.com/mcp","transport":"streamable-http","auth":"oauth","oauth":{"authProfileId":"docs:mcp"}}'
```
```bash
openclaw mcp login docs
```
OpenClaw prints the authorization URL and stores temporary OAuth verifier state in shared SQLite.
```bash
openclaw mcp login docs --code abc123
```
```bash
openclaw mcp status --verbose
openclaw mcp doctor docs --probe
```
```bash
openclaw mcp logout docs
```
If the provider rotates tokens or the authorization state gets stuck, run openclaw mcp logout <name>, then repeat login. logout can clear credentials for a saved HTTP server even after auth: "oauth" has been removed from config, as long as the server name and URL still identify the credential store entry.
streamable-http is an additional transport option alongside sse and stdio. It uses HTTP streaming for bidirectional communication with remote MCP servers.
| Field | Description |
|---|---|
url |
HTTP or HTTPS URL of the remote server (required) |
transport |
Set to "streamable-http" to select this transport; when omitted, OpenClaw uses sse |
headers |
Optional key-value map of HTTP headers (for example auth tokens) |
connectionTimeoutMs |
Per-server connection timeout in ms (optional) |
requestTimeoutMs |
Per-server MCP request timeout in milliseconds |
auth: "oauth" |
Use MCP OAuth credentials saved by openclaw mcp login |
sslVerify |
Set false only for explicitly trusted private HTTPS endpoints |
clientCert / clientKey |
mTLS client certificate and key paths |
supportsParallelToolCalls |
Hint that concurrent calls are safe for this server |
OpenClaw config uses transport: "streamable-http" as the canonical spelling. CLI-native MCP type: "http" values are accepted when saved through openclaw mcp set and repaired by openclaw doctor --fix in existing config, but transport is what embedded OpenClaw consumes directly.
Example:
{
"mcp": {
"servers": {
"streaming-tools": {
"url": "https://mcp.example.com/stream",
"transport": "streamable-http",
"connectionTimeoutMs": 10000,
"requestTimeoutMs": 30000,
"headers": {
"Authorization": "Bearer <token>"
}
}
}
}
}The browser Control UI includes a dedicated MCP settings page at /settings/mcp; the previous /mcp path remains an alias. The page shows configured server counts, enabled/OAuth/filter summaries, per-server transport rows, enable/disable controls, common CLI commands, and a scoped editor for the mcp config section.
Use the page for operator edits and quick inventory. Use openclaw mcp doctor --probe or openclaw mcp probe when you need live server proof.
Operator workflow:
- Open the Control UI and choose MCP.
- Review the summary cards for total, enabled, OAuth, and filtered servers.
- Use each server row for transport, auth, filter, timeout, and command hints.
- Toggle enablement when you want to keep a definition but exclude it from runtime discovery.
- Edit the scoped
mcpconfig section for structural changes such as new servers, headers, TLS, OAuth metadata, or tool filters. - Choose Save to persist config only, or Save & Publish to apply through the Gateway config path.
- Run
openclaw mcp doctor --probewhen you need live proof that the edited server starts and lists tools.
Notes:
- command snippets quote server names so unusual names remain copyable in a shell
- displayed URL-like values are redacted before rendering when they contain embedded credentials
- the page does not start MCP transports by itself
- active runtimes may need
openclaw mcp reload, Gateway config publish, or process restart depending on which process owns the MCP clients
OpenClaw can render tools that implement the stable MCP Apps extension. Apps are opt-in because their HTML comes from the configured MCP server and can request app-visible tools or resources from that same server.
Enable the host bridge:
openclaw config set mcp.apps.enabled true --strict-jsonRestart the Gateway after changing this setting. When enabled, OpenClaw starts a sandbox-only HTTP(S) listener on the Gateway port plus one (for the default Gateway, 18790). The Control UI loads Apps from that separate origin; the listener never serves Control UI, authenticated Gateway routes, or user data.
Direct Gateway connections need access to both ports. If a reverse proxy or TLS terminator exposes the Control UI, give Apps a dedicated public origin and proxy only that origin to the sandbox listener:
{
mcp: {
apps: {
enabled: true,
sandboxOrigin: "https://mcp-apps.example.com",
sandboxPort: 18790,
},
},
}The sandbox origin must differ from the Control UI origin. Do not host other authenticated or sensitive content on it.
For example, the official basic React demo can be configured as:
{
mcp: {
apps: { enabled: true },
servers: {
"basic-react": {
command: "npx",
args: ["-y", "@modelcontextprotocol/server-basic-react", "--stdio"],
},
},
},
}Behavior and security boundaries:
- OpenClaw advertises the
io.modelcontextprotocol/uiextension only when Apps are enabled. - Only
ui://resources with the exacttext/html;profile=mcp-appMIME type render. - UI resources are capped at 2 MiB, placed behind a double-iframe proxy on a dedicated outer origin, loaded into an opaque inner App origin, and constrained by CSP derived from the resource metadata.
- App-only tools (
_meta.ui.visibility: ["app"]) stay out of model tool lists. Apps can call only app-visible tools on their owning server that also pass the effective OpenClaw tool policy for the run that created the view. - Origin-bound App permissions such as camera, microphone, and geolocation are not granted while inner App documents use opaque origins for cross-App isolation.
- App HTML, complete tool arguments, and raw results live in a bounded ten-minute in-memory view lease and are not written to disk or copied into transcript preview metadata. The transcript stores only a bounded server/tool/resource descriptor tied to the original tool-call ID. After a Gateway restart, the Control UI can verify that descriptor against the authenticated session transcript and refetch the
ui://resource; reconstructed views are read-only until a fresh run establishes current tool permissions. - In channel conversations, the latest successful App view in a turn adds one Open App-style action to the final assistant reply. Telegram DMs use a native Mini App button; Slack and Discord render the same portable action as a link. Other channels keep the original reply text and append an understandable HTTPS link.
- Channel launch links are available only when Gateway Tailscale exposure has prepared a published HTTPS origin.
gateway.tailscale.mode: "serve"is reachable only from the tailnet;"funnel"is reachable from the public internet. An externally managed Funnel preserved bygateway.tailscale.preserveFunnelis also treated as internet-reachable. See Tailscale. - Launch tickets are opaque, minted only while materializing the final channel reply, and expire after at most two minutes or when the underlying view lease expires, whichever comes first. The URL does not contain Gateway bearer credentials, session keys, view metadata, App HTML, tool input, or tool results.
- If no published origin or ticket capacity is available, the view or ticket has expired, or the transport cannot render native controls, the original assistant text remains available. The Control UI keeps its existing inline App canvas and does not receive a duplicate launch action.
openclaw security auditwarns while the bridge is enabled. Disable it withopenclaw config set mcp.apps.enabled false --strict-jsonwhen it is not needed.
This page documents the bridge as shipped today.
Current limits:
- conversation discovery depends on existing Gateway session route metadata
- no generic push protocol beyond the Claude-specific adapter
- no message edit or react tools yet
- HTTP/SSE/streamable-http transport connects to a single remote server; no multiplexed upstream yet
permissions_list_openonly includes approvals observed while the bridge is connected