php-sdk/docs/servers/tools.md
Christopher Hertel 0cd5d56164
[Docs] Render the guides with Zensical instead of phpDocumentor (#414)
* [Docs] Render guides with Zensical, deploy via GitHub Pages actions

phpDocumentor's guide renderer copies the markdown through mostly verbatim:
relative links between pages keep pointing at `*.md` targets that do not exist
in the built site, and nothing validates them, so the published guides are full
of dead links.

Zensical (the Material for MkDocs team's successor to MkDocs) resolves internal
links against the page tree and fails the build on a broken one. `zensical
build --strict` already found four dead links on the first run — three
repo-relative links escaping docs/ (fixed to point at GitHub) and one wrong
in-page anchor.

phpDocumentor stays on for the class-level API reference only; `make docs`
builds the guides into site/ and mounts the reference at site/api/, so its two
header links back to the guides now target the site root.

Deployment moves from pushing a gh-pages branch to the official GitHub Pages
actions, and from release-only to every push on main, with pull requests
building (but not deploying) so a broken link fails review instead of the site.

NOTE: this needs the repository's Pages source switched to "GitHub Actions"
(Settings -> Pages) once.

* [Docs] Adopt the Python SDK's documentation look and feel

The docs site now uses the same theme configuration as
https://py.sdk.modelcontextprotocol.io/ so the language SDKs read as one set
of docs: the MCP mark as logo and favicon, Inter/JetBrains Mono, the
black/slate palette with a three-way (system/light/dark) toggle, instant
navigation, code copy/annotate, and a right-hand table of contents.

The markdown extension set is widened to the same list (tabbed blocks,
task lists, footnotes, emoji/icons, mermaid fences), which the content
restructure builds on.

Styling is otherwise stock: no custom stylesheet, and Zensical's own
`modern` theme variant, pinned explicitly rather than left to the default.

The one departure is code highlighting, which is broken out of the box here:
Pygments only highlights PHP after a `<?php` tag, so the guides — whose code
blocks are almost all fragments — rendered as flat plain text. The `php`
lexer is extended with `startinline`, and complete-file blocks use a
`php-file` lexer that keeps the literal open tag highlighted.

* [Docs] Restructure the guides into task-oriented sections

The guides were ten flat pages, each opening with a hand-maintained table of
contents and each mixing several audiences: `mcp-elements.md` covered tools,
prompts, schema generation and handler-side logging, `transports.md` covered
both transports plus framework integration, and `server-builder.md` covered
configuration, sessions and custom message handlers.

They are now split along the same lines as the Python SDK's documentation
(https://py.sdk.modelcontextprotocol.io/), one topic per page:

  Get started        installation, first server, the Inspector
  Servers            tools, resources, resource templates, prompts,
                     completions, schema generation, registration
  Inside your handler  the ClientGateway, logging
  Running your server  builder, STDIO, HTTP, framework integration,
                     sessions, authorization
  Clients            connecting, transports, capabilities, server-initiated
                     requests, error handling
  Advanced           events, protocol extensions, custom message handlers

Prose is carried over as-is apart from the seams; what is new is the landing
page and one index page per section, which say what the section is for and
where to go next, so no page is a dead end.

The per-page "Table of Contents" lists are gone — the theme renders one from
the headings — and GitHub's `> [!IMPORTANT]` blockquotes became admonitions,
which Zensical renders as callouts rather than plain quotes.

Every code sample and factual claim was then checked against src/ and the
runnable examples, which turned up long-standing errors in the carried-over
prose. Samples that could not run: a prompt using a `system` role (MCP has
only user/assistant), `Mcp\Schema\PromptMessage` (it is under `Schema\Content`)
constructed with an array instead of a single content object,
`Mcp\Capability\Prompt\Completion\ProviderInterface` (it is
`Mcp\Capability\Completion\ProviderInterface`), `new EmbeddedResource(type:,
resource: [...])` (neither parameter exists), a `: resource` return type
(not a PHP type), `#[McpResource]` with a `{path}` variable (that is a
template), a stray quote in the builder example, a `middlewares:` argument
(it is `middleware:`), and `getRequest()->getAttribute()` in the OAuth guide
(no such method — the values arrive on the request meta). Claims corrected:
sampling's `system_prompt` option (it is `systemPrompt`), `SampleMessage`
(it is `SamplingMessage`), `Notification` called an interface (abstract
class), "parameter order matters" for URI templates (bound by name), full
RFC 6570 support (only simple `{var}`), the tool description fallback chain,
`void` returning empty content, a non-zero STDIO exit code, `ErrorEvent`
being null for parse errors, handlers being "prepended", `Psr16StoreSession`,
and PSR-3 log context being sent to the client (it is dropped). Sixteen
`examples/` paths were missing their `server/` segment.

README, the OAuth ADR and one source comment now point at the published site
instead of at markdown files that moved.

* [Docs] Run the docs workflow unfiltered, keep README links relative

The `paths:` filters were mostly noise: `src/**` had to be in the list for
the phpDocumentor build, which meant the workflow ran on nearly every PR
anyway. They also missed two real inputs — `.phpdoc/template/**` and
`composer.lock` — so a template tweak or a phpDocumentor bump could change
the rendered site without triggering a build.

README links go back to relative repo paths. The README is not part of the
Zensical site (`docs_dir` is `docs/`), so those links are only ever resolved
by GitHub and Packagist, where absolute URLs break in-repo navigation for no
gain. The site pointer and the generated API reference stay absolute.

* [Docs] Adopt the doc changes that landed on main into the new structure

Twelve commits landed while the restructure was open, seven of them touching
the flat guides this branch replaces. Renames merged on their own; the three
files that were split apart needed their new sections placed by hand:

- Connection retries, protocol version negotiation, sampling with tools and
  roots from `client.md` into `client/connecting.md` and
  `client/server-requests.md`
- `ResourceLink` and structured output from `mcp-elements.md` into
  `servers/tools.md`
- Protocol version negotiation from `server-builder.md` into
  `run/server-builder.md`

The `setMaxRetries()` note claiming the value is never acted on is gone —
#413 implemented it. Callouts became admonitions and cross-links were
repointed at the new paths, as everywhere else in this branch.

* [Docs] Document the elicitation and roots client examples

Both were missing from the examples guide: the elicitation client predates
this branch, the roots client arrived with #395.

* [Docs] Fold the 2026-07-28 lifecycle into the new structure

Main's stateless-lifecycle.md becomes a docs/lifecycle/ section, and the pages
main touched — deprecations, the middleware split, the client's modern era —
land where the restructure moved them.

* [Docs] Link the Inspector to its documentation, not its repo

* [Docs] Distribute the 2026-07-28 material into the task sections

The Python and TypeScript SDKs file each feature where the task lives and keep
only an era comparison on its own page. Follow them: input-required moves next
to the other handler concerns, caching, subscriptions and era routing to
"Running your server", and one Protocol versions page carries the rest.

* [Docs] Move protocol version negotiation onto the Protocol versions page

The builder page keeps the setProtocolVersion() knob and links out; how a
revision is agreed now sits beside the era it belongs to.

* [Docs] Slim the README to a funnel, turn Examples into an index

* [Docs] Fix the code samples and API listings flagged by the audit

* [Docs] Link the negotiation spec section at latest, not draft
2026-08-20 00:03:54 +02:00

236 lines
8.1 KiB
Markdown

# Tools
Tools are callable functions that perform actions and return results.
```php
use Mcp\Capability\Attribute\McpTool;
class Calculator
{
/**
* Performs arithmetic operations with validation.
*/
#[McpTool(name: 'calculate')]
public function performCalculation(float $a, float $b, string $operation): float
{
return match($operation) {
'add' => $a + $b,
'subtract' => $a - $b,
'multiply' => $a * $b,
'divide' => $b != 0 ? $a / $b : throw new \InvalidArgumentException('Division by zero'),
default => throw new \InvalidArgumentException('Invalid operation')
};
}
}
```
## Parameters
- **`name`** (optional): Tool identifier. Defaults to method name if not provided.
- **`title`** (optional): Human-readable display title shown in client UI. Distinct from `name`.
- **`description`** (optional): Tool description. Falls back to the docblock (summary plus long description); stays unset if there is no docblock.
- **`annotations`** (optional): `ToolAnnotations` object for additional metadata.
- **`outputSchema`** (optional): JSON schema describing `structuredContent`; see [Structured Output](#structured-output).
- **`icons`** (optional): Array of `Icon` objects for visual representation.
- **`meta`** (optional): Arbitrary key-value pairs for custom metadata.
**Priority**: `name` is the attribute parameter, else the method name. `description` is the attribute parameter, else the docblock — the method name is never used as a description.
For tool parameter validation and JSON schema generation, see [Schema generation](schemas.md).
## Tool Return Values
Tools can return any data type and the SDK will automatically wrap them in appropriate MCP content types.
### Automatic Content Wrapping
```php
// Primitive types → TextContent
public function getString(): string { return "Hello"; } // TextContent
public function getNumber(): int { return 42; } // TextContent
public function getBool(): bool { return true; } // TextContent
public function getArray(): array { return ['key' => 'value']; } // TextContent (JSON)
// Special cases
public function getNull(): ?string { return null; } // TextContent("(null)")
public function returnVoid(): void { /* no return */ } // TextContent("(null)")
```
### Explicit Content Types
For fine control over output formatting:
```php
use Mcp\Schema\Content\{TextContent, ImageContent, AudioContent, ResourceLink, EmbeddedResource};
public function getFormattedCode(): TextContent
{
return TextContent::code('<?php echo "Hello";', 'php');
}
public function getMarkdown(): TextContent
{
return new TextContent('# Title\n\nMarkdown content');
}
public function getImage(): ImageContent
{
return new ImageContent(
data: base64_encode(file_get_contents('image.png')),
mimeType: 'image/png'
);
}
public function getAudio(): AudioContent
{
return new AudioContent(
data: base64_encode(file_get_contents('audio.mp3')),
mimeType: 'audio/mpeg'
);
}
public function getEmbeddedResource(): EmbeddedResource
{
return EmbeddedResource::fromText('file://data.json', 'File content');
// …or build the resource contents yourself:
// return new EmbeddedResource(
// new TextResourceContents('file://data.json', 'application/json', '{}')
// );
}
public function getResourceLink(): ResourceLink
{
// Reference a resource by URI without embedding its contents, e.g. when
// a tool result would otherwise need to inline many or large resources.
return new ResourceLink(
uri: 'file://data.json',
name: 'data.json',
mimeType: 'application/json'
);
}
```
### Multiple Content Items
Return an array of content items:
```php
public function getMultipleContent(): array
{
return [
new TextContent('Here is the analysis:'),
TextContent::code($code, 'php'),
new TextContent('And here is the summary.')
];
}
```
### Structured Output
Besides the human-readable `content`, a tool result can carry a machine-readable `structuredContent` value. Declare its
shape with `outputSchema`, a JSON Schema of type `object`:
```php
#[McpTool(
name: 'get_weather',
outputSchema: [
'type' => 'object',
'properties' => [
'temperature' => ['type' => 'number'],
'conditions' => ['type' => 'string'],
],
'required' => ['temperature', 'conditions'],
]
)]
public function getWeather(string $city): array
{
// Sent as `structuredContent`, and JSON-encoded into `content` for clients that ignore it
return ['temperature' => 22.5, 'conditions' => 'sunny'];
}
```
The same schema can be passed to manual registration:
```php
$builder->addTool([WeatherHandler::class, 'getWeather'], outputSchema: [/* ... */]);
```
The SDK fills `structuredContent` whenever the return value qualifies — `outputSchema` is what tells clients to expect it
and lets them validate it. What qualifies depends on the protocol revision the call is served under:
| Return value | `structuredContent` |
|---|---|
| Associative array (`['temperature' => 22.5]`) | The array |
| Object (`stdClass`, DTO, `JsonSerializable`) that serializes to a JSON object | Its JSON representation |
| List (`[1, 2, 3]`, `[['id' => 1], ['id' => 2]]`), or an object serializing to one | Omitted before `2026-07-28`, kept from it on |
| Array holding `Content` instances | Omitted (already carried in `content`) |
| Scalars, `null`, `Content` instances | Omitted |
Up to revision `2025-11-25`, `structuredContent` had to be a JSON object, so a PHP list — which serializes to a JSON
array — was not emittable and strict clients rejected the whole tool call over one. [SEP-2106][sep-2106], part of
revision `2026-07-28`, widened `outputSchema` to any JSON Schema 2020-12 and `structuredContent` to any JSON value
conforming to it. The SDK picks the rule from the revision negotiated for the call, so a tool serving both eras needs the
object shape to produce structured output everywhere. Wrap the list in a key for that:
```php
// Structured content only from 2026-07-28 on: a bare list is not a JSON object
public function listUsersFlat(): array
{
return [['id' => 1], ['id' => 2]];
}
#[McpTool(outputSchema: [
'type' => 'object',
'properties' => [
'items' => ['type' => 'array', 'items' => ['type' => 'object']],
],
'required' => ['items']
])]
public function listUsers(): array
{
return ['items' => [['id' => 1], ['id' => 2]]];
}
```
Either way the data reaches the client: a return value with no structured representation is still JSON-encoded into
`content` as a `TextContent`. When a tool declares an `outputSchema` but returns something that cannot be sent as
`structuredContent`, the SDK logs a warning — the value is not silently dropped.
A tool that wants to branch on the revision itself can read it from the injected `RequestContext`, see
[Talking back to the client](../handlers/client-communication.md#clientgateway).
[sep-2106]: https://modelcontextprotocol.io/specification/2026-07-28/server/tools#structured-content
### Error Handling
Tool handlers can throw any exception, but the type determines how it's handled:
- **`ToolCallException`**: Converted to JSON-RPC response with `CallToolResult` where `isError: true`, allowing the LLM to see the error message and self-correct
- **Any other exception**: Converted to JSON-RPC error response, but with a generic error message
```php
use Mcp\Exception\ToolCallException;
#[McpTool]
public function divideNumbers(float $a, float $b): float
{
if ($b === 0.0) {
throw new ToolCallException('Division by zero is not allowed');
}
return $a / $b;
}
#[McpTool]
public function processFile(string $filename): string
{
if (!file_exists($filename)) {
throw new ToolCallException("File not found: {$filename}");
}
return file_get_contents($filename);
}
```
**Recommendation**: Use `ToolCallException` when you want to communicate specific errors to clients. Any other exception will still be converted to JSON-RPC compliant errors but with generic error messages.