MCP Servers

KnightCode connects to Model Context Protocol servers over stdio or streamable HTTP and makes their tools and resources available to the model.

Quick setup

Add a local stdio server, check the connection, then start KnightCode:

knightcode mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem .
knightcode mcp list
knightcode

For a remote server:

knightcode mcp add docs --url https://example.com/mcp --bearer-token-env-var DOCS_TOKEN
knightcode mcp list

These commands add user-level servers by default. Add --local or -l to write the project configuration instead:

knightcode mcp add -l tools --env API_KEY='${TOOLS_KEY}' -- uvx tools-mcp

Plugins can bring MCP servers too; they connect next to these and are listed by /mcp.

Use /mcp inside an interactive session to inspect connections, sign in, reconnect, change exposure, or enable and disable servers. Run /reload after adding, removing, or changing a server outside the session.

Configure servers

KnightCode reads user-level servers from ~/.knightcode/agent/mcp.json and project servers from .knightcode/mcp.json. Project configuration is read only after project trust is granted. A project entry replaces a user-level entry with the same name.

A project entry without command, url, or type overrides only enabled, exposure, and toolExposure of the user-level server with the same name and keeps the rest, including env, headers, and auth. For example, this turns off a user-level server in one project:

{
  "mcpServers": {
    "internal-tools": { "enabled": false }
  }
}

The format matches other MCP clients:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
    },
    "docs": {
      "url": "https://example.com/mcp",
      "headers": { "Authorization": "Bearer ${DOCS_TOKEN}" },
      "description": "Search and read the product documentation"
    }
  }
}

Stdio servers use command, args, env, and cwd. Relative cwd values resolve against the session directory. A leading ~/ in command, an argument, or cwd names the home directory.

HTTP servers use url, headers, and oauth (see Authenticate with OAuth). The legacy SSE transport is not supported.

Both server types support:

• timeout: per-request timeout in seconds (default 60). Progress notifications reset it.
• enabled: false: keep the entry without connecting to it.
• exposure and toolExposure: control how tools reach the model (see Control tool exposure).
• description: what the server offers, in a sentence. For servers with codemode or deferred tools, it describes the server in the system prompt's server list (see Control tool exposure), tool search ranks the server's tools by it, and codemode's describeNamespace() returns it. Without it, the first line of the server instructions is used once the server connects.

Keep personal servers and servers with credentials in the user-level file. Use the project file only for servers the project requires, and only in trusted projects.

Configuration rules

• Server names may contain only letters, digits, _, and -. Tools are named mcp__<server>__<tool>, with every character other than letters, digits, and _ replaced by _; tools of a server whose names then collide all get a hash suffix. Server names that differ only in - and _ count as the same server: a second one is rejected, and a mcp.json server overrides a registered one.
• type is optional. A command selects stdio and a url selects streamable HTTP. When present, type must be stdio, http, or streamable-http.
• sse is rejected. Servers that document an SSE endpoint often also provide streamable HTTP, commonly at /mcp instead of /sse.
• command is one executable and args contains its arguments. It is not a shell command string.
• env and headers values can use environment variables such as ${GITHUB_TOKEN}. They can also run a command with !command, but the command must make up the whole value, for example "Authorization": "!echo Bearer $(gh auth token)".
• Invalid entries are reported and skipped without preventing other servers from connecting.

knightcode mcp add and knightcode mcp remove cover common changes from a shell. See MCP commands for their options.

Inspect or change a server

/mcp lists configured servers with their state, tool count, exposure, and configuration source. Servers that need attention appear first. Select a server to inspect its tools and connection details, reconnect, sign in or out, change exposure, or enable and disable it.

Exposure and enabled-state changes are saved to the file that defines the server without replacing unrelated content. In a trusted project, "Enable in this project" and "Disable in this project" add a project override for a user-level server; later changes to that server are saved to the override. Disabled servers remain listed. Outside the interactive TUI, /mcp prints server status; /mcp login <server>, /mcp logout <server>, and /mcp reconnect <server> perform those actions directly.

Shell commands work without a session: knightcode mcp add, knightcode mcp remove, knightcode mcp list, knightcode mcp login, and knightcode mcp logout. Shell commands do not load extensions.

Diagnose connection problems

Run knightcode mcp list to connect to every enabled server and print its state, tools, and errors. It exits with status 1 when an entry is invalid or an enabled server is not connected. /mcp shows the full connection error and the tail of stderr from a failed stdio server.

KnightCode reports configuration errors, failed connections, and required sign-ins once after startup. Server logging notifications are appended to ~/.knightcode/agent/mcp.log as <time> [<server>] <level> <logger>: <message>. The file moves to mcp.log.1 after it grows past 5 MB.

KnightCode connects every enabled server in the background when a session starts. A server's tools appear once it connects; the codemode description does not list them, so it does not change when servers connect. The first prompt waits up to 10 seconds only for servers with direct tools, which must be declared in its request. Other servers are waited for when they are needed: a codemode script waits for the servers it names (mcp__<server>) and, when it calls searchTools() or reads ALL_TOOLS, for all of them; tool_search and the resource tools also wait for all of them. HTTP network errors and transient statuses (408, 429, and 5xx) are retried twice. A dropped connection is shown as disconnected and reconnects on the next call. When a server announces a changed tool list, new tools are added and withdrawn tools become unreachable.

Stopping a stdio server closes its stdin, sends SIGTERM, then sends SIGKILL to its process group. This also stops servers launched through wrappers such as npx or uvx.

Migrate configuration from another client

Move the converted entry under mcpServers in mcp.json, then run knightcode mcp list to validate it.

Authenticate with OAuth

Remote servers that use OAuth, such as Sentry, need no credentials in mcp.json:

{
  "mcpServers": {
    "sentry": { "url": "https://mcp.sentry.dev/mcp" }
  }
}

When the server rejects an unauthenticated connection, /mcp shows that it needs sign-in. Select "Sign in", run /mcp login sentry, or run knightcode mcp login sentry. KnightCode opens the authorization page and waits for approval. If the browser runs on another machine, such as over SSH, paste its redirected URL into the sign-in screen. A running session uses the new credentials on its next turn.

KnightCode identifies itself to the authorization server with its Client ID Metadata Document or by registering a client, stores tokens in ~/.knightcode/agent/mcp-auth.json, and refreshes access tokens when they expire or the server rejects them. If a server later requests additional scope, KnightCode asks for sign-in again and names the missing scope; the new sign-in requests it on top of what was granted. Signing out deletes the stored credentials.

Credentials belong to a server name and URL. Servers with the same URL under different names, such as one per account, sign in separately; servers with the same name and URL in different mcp.json files share one sign-in.

OAuth applies to HTTP servers without an Authorization header. For a server that does not support dynamic client registration, configure a registered client:

{
  "mcpServers": {
    "example": {
      "url": "https://mcp.example.com/mcp",
      "oauth": { "clientId": "my-client", "clientSecret": "${EXAMPLE_SECRET}", "callbackPort": 8765 }
    }
  }
}

The redirect URI must match the registered URI. callbackPort uses http://127.0.0.1:<port>/callback. To use another URI, set callbackUrl; it must use HTTP on localhost, 127.0.0.1, or [::1]. KnightCode sends it exactly as written. When callbackUrl omits a port, KnightCode uses callbackPort or a free port and adds it to the URI, as allowed for loopback redirects by RFC 8252. clientSecret is optional and can use an environment variable or command.

Set scope to a space-separated list for servers that do not advertise their required scopes. Otherwise, KnightCode requests the advertised scopes. Later scope requests are added to the configured value.

KnightCode registers as knightcode. Some servers only accept registrations from known clients. Set clientName to send another name:

{
  "mcpServers": {
    "figma": { "url": "https://mcp.figma.com/mcp", "oauth": { "clientName": "Claude Code" } }
  }
}

The name is only sent when KnightCode registers a client. To register again under a new name, sign out first.

Without clientId, KnightCode identifies itself with its Client ID Metadata Document on knightcode.dev when the authorization server advertises support for documents and public clients. Otherwise it registers a client dynamically. A client registered before stays in use while its redirect URI matches, until you sign out. With the document, the client ID is https://knightcode.dev/oauth/client.json with the redirect URI http://127.0.0.1:<port>/callback. If the authorization server does not send the iss parameter in authorization responses (RFC 9207), KnightCode uses a document and redirect path specific to the MCP server instead: https://knightcode.dev/oauth/<id>/client.json with http://127.0.0.1:<port>/callback/<id>.

KnightCode registers instead of using the document when clientName is set or callbackUrl is not /callback on localhost or 127.0.0.1. Set clientRegistration to choose the method: auto (default) as described, dcr to always register, or cimd to always use the document. With cimd, sign-in fails if the authorization server does not support documents for public clients. Use dcr when the authorization page reports an invalid client:

{
  "mcpServers": {
    "example": { "url": "https://mcp.example.com/mcp", "oauth": { "clientRegistration": "dcr" } }
  }
}

knightcode mcp add --oauth-client-registration <mode> sets it when adding a server. cimd cannot be combined with clientId or clientName, and a callbackUrl must use localhost or 127.0.0.1 with the path /callback.

KnightCode finds the authorization server through the server's protected resource metadata (RFC 9728) and checks that the authorization server's metadata names the expected issuer (RFC 8414). Some servers advertise the wrong authorization server or none, so sign-in opens a page that does not exist. Set authServerMetadataUrl to the metadata document of the right authorization server:

{
  "mcpServers": {
    "example": {
      "url": "https://mcp.example.com/mcp",
      "oauth": { "authServerMetadataUrl": "https://example.okta.com/.well-known/openid-configuration" }
    }
  }
}

KnightCode uses that document instead of discovery and trusts it as configured, so only point it at a document you trust. The URL must use HTTPS, except on localhost, 127.0.0.1, or [::1].

Control tool exposure

Each server tool is registered as mcp__<server>__<tool>. The server's exposure determines how the model reaches it:

codemode-deferred is accepted as an alias for codemode.

Servers with codemode or deferred tools are listed in the mcp_servers section of the system prompt, with how their tools are reached and one line from the configured description or, once connected, from the server instructions. KnightCode updates the section when a prompt starts, after waiting for servers with direct tools. When it changed, for example because a server connected and its summary became available, KnightCode appends the new section to the conversation instead of changing tool declarations, so earlier messages stay cached. describeNamespace() and the namespace option of searchTools() accept mcp__dev-radius, mcp__dev_radius, dev-radius, or dev_radius.

KnightCode activates codemode when a server with codemode exposure connects. It activates tool_search for a server with deferred exposure. To make the model see a tool without searching, give it direct exposure with toolExposure.

toolExposure overrides the server exposure for individual tools. Keys are exact server tool names or patterns where * matches any characters. Exact names win over patterns; among patterns, the first match wins. A server with hidden exposure can expose only selected tools:

{
  "mcpServers": {
    "github": {
      "url": "https://api.githubcopilot.com/mcp/",
      "exposure": "deferred",
      "toolExposure": {
        "search_code": "direct",
        "get_*": "codemode",
        "delete_*": "hidden"
      }
    }
  }
}

knightcode mcp list marks tools whose exposure differs from their server. The Tools view in /mcp also shows the effective exposure.

Tools with codemode or deferred exposure can be reached through either indirect mechanism: codemode scripts can call them, and tool_search can load them. Codemode calls do not depend on the active tool set, so they remain available after /tree, resume, and fork. Tools loaded by tool_search are recorded in the transcript and remain declared on that branch.

--tools does not remove MCP tools unless one of its entries starts with mcp__; knightcode --tools read,codemode,'mcp__radius__*' keeps only the tools of radius. --exclude-tools accepts the same patterns, and --no-mcp disables MCP for one run (see Tools).

To keep codemode active without MCP servers, add "defaultTools": ["+codemode"] to settings. To prevent automatic codemode activation, set "autoEnableCodemode": false beside mcpServers. A project value overrides the user-level value. KnightCode warns once when neither codemode nor tool_search is active and non-direct tools cannot be called.

Text results over 20 KB reach the model with their middle removed around a …N chars truncated… marker. The full text is saved to a temporary file named in the result. Codemode scripts receive the complete result and can reduce it before returning output to the model.

Codemode scripts receive the complete MCP CallToolResult, including content, structuredContent, and isError. A result with isError resolves inside scripts but is reported as an error for direct calls. image(result.content[0]) forwards an image block. Server instructions are not part of any tool description; scripts read them with describeNamespace("mcp__<server>"), which also returns the server's tool names.

Use resources

When a connected server offers resources, KnightCode adds the resource tools used by Codex and OpenCode:

• list_mcp_resources lists resources as JSON: { server?, resources: [{ server, uri, name, ... }], nextCursor? }. With server, it lists one page; cursor continues with the next page. Without server, it lists every resource from every server.
• list_mcp_resource_templates lists URI templates for resources the servers do not list directly.
• read_mcp_resource reads a resource by server and uri. Text reaches the model as text and images as images. Other binary resources are saved to temporary files, and the model receives the path. Scripts receive { server, uri, contents }.

These tools reach every enabled, non-hidden server with resources. Their exposure is the widest exposure among those servers: direct, then codemode or deferred. Resource links in tool results identify read_mcp_resource and the server.

Resources for MCP Apps, identified by ui:// URIs or text/html;profile=mcp-app, are omitted from these tools: the desktop app draws them (see MCP Apps). Resource icons are also omitted.

Reading and listing resources is retried once after a transient HTTP error (408, 429, or 5xx). Tool calls are not retried because the server may already have performed them.

MCP Apps

A server can give a tool an interactive view with the MCP Apps extension (io.modelcontextprotocol/ui, Stable 2026-01-26): the tool names a ui:// resource in _meta.ui.resourceUri, and the resource is an HTML document of type text/html;profile=mcp-app. The desktop app draws it in the tool's row. The terminal draws no apps, so KnightCode tells servers it supports them only in the desktop, and elsewhere servers answer with their text fallback.

In the desktop:

• A tool with an app is declared to the model whatever the server's exposure, and it cannot be called from codemode scripts: a call drawn as an app must be the model's own, which the session keeps. A tool you configured as hidden stays hidden and draws no app.
• A tool whose _meta.ui.visibility leaves out "model" is not declared to the model, whatever its exposure and whether or not it has an app of its own. An app can still call it.
• An app calls only tools of its own server whose visibility includes "app". In Full access its calls run. In Ask and Auto-edit, a call to a tool not annotated readOnlyHint asks you first, naming the server and the tool. An app's calls do not go through the session's tool pipeline, so extension tool_call and tool_result handlers, permission gates included, do not see them.
• An app can send a follow-up message to the thread after you confirm it, open http and https links in your browser, and ask to be shown full screen in the side panel. It cannot update the model's context.
• The app runs in a sandboxed frame on its own origin, with no permissions (no camera, microphone, location or clipboard). It reaches the network only through the domains its resource declares in _meta.ui.csp; a declaration that is not a list of host sources is refused and the app does not load.

examples/mcp-app/server.mjs is a small stdio server with a counter app: one tool that shows the app, one only the app may call, and one read-only tool.

Permissions

Every MCP call the model makes passes through KnightCode's tool pipeline. Extension tool_call and tool_result handlers, including permission gates, therefore apply to MCP tools; an MCP App's own calls are the exception. Calls made from codemode scripts carry the codemode call ID as parentToolCallId.

knightcode.getAllTools() reports the annotations declared by each server: readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. Permission extensions can use these hints to decide which calls require confirmation (see Tool exposure). Resource tools are marked read-only.

Extensions and SDK

Add servers from extensions

Extensions can add servers for the current session with knightcode.registerMcpServer(name, config), using the same shape as an mcpServers entry (see MCP servers in extensions). Registered servers connect like configured servers and appear in /mcp with the extension as their source.

Changes to enabled state or exposure apply only to the current session. A file-configured server with the same name takes precedence, and /mcp lists the overridden registration. knightcode mcp shell commands do not load extensions and only see file-configured servers.

Replace the built-in MCP support

An installed extension that registers /mcp, such as knightcode-mcp-adapter, replaces the built-in MCP support for sessions. KnightCode then does not read mcp.json or connect its servers in a session, and /mcp belongs to the extension. Remove the extension to restore the built-in behavior. To disable built-in MCP support without a replacement, disable mcp under Built-in in knightcode config, or set "extensions": ["-builtin:mcp"] in settings. --no-mcp disables it for one run.

An extension that registers codemode or tool_search similarly replaces the built-in tool with that name. KnightCode activates the replacement for MCP servers and waits for the servers its calls need only when it declares reachesTools. Shell-level knightcode mcp commands always use the built-in implementation.

Use MCP from the SDK

SDK sessions do not load built-in extensions. Add the MCP extension, the codemode extension for codemode servers, and the tool-search extension for deferred servers to the resource loader. See Codemode and MCP.