Skip to content

SEP-1034 : Support default values for all primitive types in elicitation schemas #1034

Closed

Description

@chughtapan

Preamble

Title: Support default values for all primitive types in elicitation schemas
Author: Tapan Chugh ([email protected])
Status: Accepted
Type: Standards Track
Created: 2025-07-22
Accepted: 2025-08-22

Abstract

This SEP recommends adding support for default values to all primitive types in the MCP elicitation schema (StringSchema, NumberSchema, and EnumSchema), extending the existing support that only covers BooleanSchema.

Motivation

Elicitations in MCP offer a way to mitigate complex API designs: tools can request information on-demand rather than resorting to convoluted parameter handling. The challenge however is that users must manually enter obvious information that could be pre-populated for more natural interactions. Currently, only BooleanSchema supports default values in elicitation requests. This limitation prevents servers from providing sensible defaults for text inputs, numbers, and enum selections leading to more user overhead.

Real-World Example

Consider implementing an email reply function. Without elicitation, the tool becomes unwieldy:

def reply_to_email_thread(
    thread_id: str, 
    content: str, 
    recipient_list: List[str] = [], 
    cc_list: List[str] = []
) -> None:
    # Ambiguity: Does empty list mean "no recipients" or "use defaults"?
    # Complex logic needed to handle different combinations

With elicitation, the tool signature itself can be much simpler

def reply_to_email_thread(
    thread_id: str, 
    content: Optional[str] = ""
) -> None:
    # Code can lookup the participants from the original thread 
    # and prepare an elicitation request with the defaults setup
const response = await client.request("elicitation/create", {
  message: "Configure email reply",
  requestedSchema: {
    type: "object",
    properties: {
      recipients: {
        type: "string",
        title: "Recipients",
        default: "[email protected], [email protected]"  // Pre-filled
      },
      cc: {
        type: "string",
        title: "CC",
        default: "[email protected]"  // Pre-filled
      },
      content: {
        type: "string",
        title: "Message"
        default: "" // If provided in the tool above
      }
    }
  }
});

Implementation

A working implementation demonstrating clients require minimal changes to display defaults (~10 lines of code):

Specification

Schema Changes

Extend the elicitation primitive schemas to include optional default values:

export interface StringSchema {
  type: "string";
  title?: string;
  description?: string;
  minLength?: number;
  maxLength?: number;
  format?: "email" | "uri" | "date" | "date-time";
  default?: string;  // NEW
}

export interface NumberSchema {
  type: "number" | "integer";
  title?: string;
  description?: string;
  minimum?: number;
  maximum?: number;
  default?: number;  // NEW
}

export interface EnumSchema {
  type: "string";
  title?: string;
  description?: string;
  enum: string[];
  enumNames?: string[];
  default?: string;  // NEW - must be one of enum values
}

// BooleanSchema already has default?: boolean

Behavior

  1. The default field is optional, maintaining full backward compatibility
  2. Default values must match the schema type
  3. For EnumSchema, the default must be one of the valid enum values
  4. Clients that support defaults SHOULD pre-populate form fields. Clients that don't support defaults MAY ignore the field entirely.

Rationale

  1. The high-level rationale is to follow the precedent set by BooleanSchema rather than creating new mechanisms.
  2. Making defaults optional ensures backward compatibility.
  3. This maintains the high-level intuition of keeping the client implementation simple.

Alternatives Considered

  1. Server-side Templates: Servers could maintain templates separately, but this adds complexity
  2. New Request Type: A separate request type for forms with defaults would fragment the API
  3. Required Defaults: Making defaults required would break existing implementations

Backwards Compatibility

This change is fully backward compatible with no breaking changes. Clients that don't understand defaults will ignore them, and existing elicitation requests continue to work unchanged. Clients can adopt default support at their own pace

Security Implications

No new security concerns:

  1. No Sensitive Data: The existing guidance against requesting sensitive information still applies
  2. Client Control: Clients retain full control over what data is sent to servers
  3. User Visibility: Default values are visible to users who can modify them before submission

Activity

  1. self-assigned this
    on Jul 24, 2025
  2. changed the title [-]SEP: Support default values for all primitive types in elicitation schemas[/-] [+]SEP 1034 : Support default values for all primitive types in elicitation schemas[/+] on Jul 24, 2025
  3. changed the title [-]SEP 1034 : Support default values for all primitive types in elicitation schemas[/-] [+]SEP-1034 : Support default values for all primitive types in elicitation schemas[/+] on Jul 24, 2025
  4. pcarleton commented on Aug 15, 2025

    @pcarleton
    Member

    Thanks for the great demo showing how it can be used.

    I can see this being useful for write tools that want to allow final edits before the user hits send, e.g. the full "content" could be pre-filled, and the user could edit it first. It can be annoying otherwise if you get a "accept/decline" elicitation, and you have to say "no" and try to get the model to fix the arguments.

  5. chughtapan commented on Aug 15, 2025

    @chughtapan
    ContributorAuthor

    Thanks @pcarleton

    I agree - a great place to showcase this with a git commit tool. The model gets the commit message mostly correct, but I always want to refine it a bit. I've been thinking that the git reference server might be the perfect place to showcase the UX improvements here and in #1330.

  6. moved this from In Review to Review Batch in SEP Review Pipelineon Aug 21, 2025
  7. added
    acceptedSEP accepted by core maintainers, but still requires final wording and reference implementation.
    and removed
    draftSEP proposal with a sponsor.
    in-reviewSEP proposal ready for review.
    on Aug 22, 2025
  8. moved this from Review Batch to Accepted in SEP Review Pipelineon Aug 22, 2025
  9. cliffhall commented on Sep 1, 2025

    @cliffhall
    Member

    Closing as this SEP was accepted and its implementation merged:
    #1035 (review)

  10. moved this from Backlog to In progress in 2025-11-25 Implementationon Nov 5, 2025
  11. dend commented on Nov 12, 2025

    @dend
    Contributor

    Linked to #1035

  12. added this to the DRAFT-2025-11-25 milestone on Nov 13, 2025
  13. moved this from Accepted to Final in SEP Review Pipelineon Aug 23, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

SEPacceptedSEP accepted by core maintainers, but still requires final wording and reference implementation.awaiting-sdk-changefinalSEP finalized.

Type

No type

Projects

Relationships

None yet

Development

No branches or pull requests

Issue actions