Merge pull request #417 from koic/json_schema_2020_12_tool_schemas

Conform Tool Schemas to JSON Schema 2020-12 per SEP-2106
This commit is contained in:
Koichi ITO 2026-06-24 13:39:16 +09:00 • committed by GitHub
commit 7e878827ae
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 303 additions and 25 deletions

View file

@ -636,7 +636,7 @@ module MCP
tool, arguments, server_context_with_meta(request), progress_token: progress_token, session: session, related_request_id: related_request_id, cancellation: cancellation
)
validate_tool_call_result!(tool, result)
result
serialize_structured_content_fallback(result)
rescue RequestHandlerError, CancelledError
# CancelledError is intentionally not wrapped so `handle_request` can turn it into
# `JsonRpcHandler::NO_RESPONSE` per the MCP cancellation spec.
@ -801,6 +801,18 @@ module MCP
tool.output_schema.validate_result(result[:structuredContent])
end
# Per SEP-2106, `structuredContent` may be any JSON value, not only an object.
# Clients on older protocol versions may only read `content`,
# so when a tool returns non-object structured content without providing
# any content blocks, mirror the value into `content` as serialized JSON text.
def serialize_structured_content_fallback(result)
structured = result[:structuredContent]
return result if structured.nil? || structured.is_a?(Hash)
return result unless result[:content].nil? || result[:content].empty?
result.merge(content: [{ type: "text", text: JSON.generate(structured) }])
end
# Whether a tool/prompt handler opts in to receiving an `MCP::ServerContext`.
# Recognizes `:keyrest` (`**kwargs`) because tools are invoked without a positional argument
# (`tool.call(**args, server_context:)`), soa `**kwargs`-only signature safely captures `server_context:`.

View file

@ -7,12 +7,29 @@ module MCP
class OutputSchema < Schema
class ValidationError < StandardError; end
# Root-level keywords whose presence means the user already chose a root schema shape,
# so no `type: "object"` default should be merged in.
ROOT_SCHEMA_KEYWORDS = [:type, :"$ref", :oneOf, :anyOf, :allOf, :not, :if, :const, :enum].freeze
def validate_result(result)
errors = fully_validate(result)
if errors.any?
raise ValidationError, "Invalid result: #{errors.join(", ")}"
end
end
private
# Per SEP-2106, an output schema may be ANY valid JSON Schema 2020-12 document: object, array, primitive,
# or a root-level composition.
# Default the root to an object only when no root schema keyword is present, which preserves the wire output
# of the common `properties`-only shape while leaving e.g. `{ type: "array" }` or `{ oneOf: [...] }` untouched
# (the old unconditional default merged `type: "object"` into root combinators, producing a wrong schema).
def apply_default_root_type!
return if ROOT_SCHEMA_KEYWORDS.any? { |keyword| @schema.key?(keyword) }
super
end
end
end
end

View file

@ -36,16 +36,29 @@ module MCP
end
VALIDATION_CACHE = ValidationCache.new
# JSON Schema 2020-12 is the default dialect for MCP schema definitions
# per MCP 2025-11-25 (SEP-1613). Note: emission only — runtime validation
# is still performed against the JSON Schema draft-04 metaschema.
# JSON Schema 2020-12 is the default dialect for MCP schema definitions per MCP 2025-11-25 (SEP-1613),
# and SEP-2106 requires tool schemas to conform to the full 2020-12 vocabulary. Both emission and
# runtime validation use this dialect. Because MCP mandates 2020-12, the SDK validates against it
# regardless of any `$schema` a document embeds; for compliant schemas this is the same dialect
# the Python SDK's `jsonschema.validate` resolves to.
JSON_SCHEMA_2020_12_URI = "https://json-schema.org/draft/2020-12/schema"
DRAFT4_META_SCHEMA_URI = "http://json-schema.org/draft-04/schema#"
# Resource bounds for schema compilation, mirroring the TypeScript SDK's schema bounds (SEP-2106):
# schemas may use the full JSON Schema 2020-12 vocabulary including composition keywords and `$ref`,
# so adversarial documents must be rejected before they can cause excessive validation cost.
# Only same-document references (starting with `#`) are accepted, so schema handling can never trigger network
# or file access.
MAX_SCHEMA_DEPTH = 64
MAX_SUBSCHEMA_COUNT = 10_000
# Reference keywords whose targets the SDK refuses to dereference. Both `$ref` and `$dynamicRef` may carry
# an absolute URI under JSON Schema 2020-12, so a non-same-document value is an external reference.
REFERENCE_KEYWORDS = [:"$ref", :"$dynamicRef"].freeze
def initialize(schema = {})
@schema = JSON.parse(JSON.dump(schema), symbolize_names: true)
@schema[:type] ||= "object"
apply_default_root_type!
validate_schema_bounds!
validate_schema!
end
@ -61,6 +74,48 @@ module MCP
private
# Root-type defaulting hook. The base class preserves the historical behavior of defaulting the root
# to an object schema; `OutputSchema` overrides this because SEP-2106 allows any root schema there.
def apply_default_root_type!
@schema[:type] ||= "object"
end
# Enforces `MAX_SCHEMA_DEPTH` / `MAX_SUBSCHEMA_COUNT` and the same-document reference rule over
# the whole schema document.
def validate_schema_bounds!
subschema_count = 0
stack = [[@schema, 1]]
until stack.empty?
node, depth = stack.pop
if depth > MAX_SCHEMA_DEPTH
raise ArgumentError,
"Invalid JSON Schema: nesting exceeds the maximum depth of #{MAX_SCHEMA_DEPTH}."
end
case node
when Hash
subschema_count += 1
if subschema_count > MAX_SUBSCHEMA_COUNT
raise ArgumentError,
"Invalid JSON Schema: document exceeds the maximum of #{MAX_SUBSCHEMA_COUNT} subschema objects."
end
REFERENCE_KEYWORDS.each do |keyword|
ref = node[keyword]
next unless ref.is_a?(String) && !ref.start_with?("#")
raise ArgumentError,
"Invalid JSON Schema: only same-document #{keyword} (starting with '#') is supported, got #{ref.inspect}."
end
node.each_value { |child| stack << [child, depth + 1] }
when Array
node.each { |child| stack << [child, depth + 1] }
end
end
end
def stringify(obj)
case obj
when Hash
@ -78,13 +133,16 @@ module MCP
# Memoized per Schema instance because schema content is fixed at construction,
# so the compiled schemer is reusable across many `fully_validate` calls.
#
# Validated against the JSON Schema 2020-12 metaschema per SEP-2106, so `$defs`/`$ref` and
# the rest of the 2020-12 vocabulary resolve natively.
#
# `format: false` preserves the legacy behavior of the previous `json-schema` based implementation,
# which did not enforce `format` keywords. `RegexpError` from a malformed `pattern` is re-raised as
# `ArgumentError` so callers see the same exception class they used to.
def schemer
@schemer ||= JSONSchemer.schema(
stringify(schema_for_validation),
meta_schema: DRAFT4_META_SCHEMA_URI,
meta_schema: JSON_SCHEMA_2020_12_URI,
format: false,
)
rescue RegexpError => e
@ -112,8 +170,8 @@ module MCP
VALIDATION_CACHE.store(key)
end
# `json_schemer` is pinned to the draft-04 metaschema, so strip top-level `$schema` before validation:
# this preserves the legacy behavior of ignoring the advertised dialect URI when the SDK validates schemas.
# Strip the top-level `$schema` before validation so the SDK always validates against
# the 2020-12 metaschema (SEP-2106) regardless of any dialect URI a caller embedded in the document.
def schema_for_validation
return @schema unless @schema.key?(:"$schema")