Meilisearch MCP Server

update-filterable-attributes

Modify which fields can be used to filter search results in a Meilisearch index, enabling precise data retrieval through attribute-based filtering.

Instructions

Update the filterable attributes setting

Input Schema

TableJSON Schema

Name	Required	Description	Default
`indexUid`	Yes	Unique identifier of the index
`value`	Yes	JSON value for the setting

Implementation Reference

src/tools/settings-tools.ts:236-248 (handler)

Handler that parses the JSON value input, performs a PUT request to update the filterable-attributes setting via apiClient, and returns the response or error.

async ({ indexUid, value }) => {
  try {
    // Parse the value string to ensure it's valid JSON
    const parsedValue = JSON.parse(value);
    
    const response = await apiClient.put(`/indexes/${indexUid}/settings/${endpoint}`, parsedValue);
    return {
      content: [{ type: "text", text: JSON.stringify(response.data, null, 2) }],
    };
  } catch (error) {
    return createErrorResponse(error);
  }
}

src/tools/settings-tools.ts:232-235 (schema)

Zod input schema defining indexUid and value parameters.

{
  indexUid: z.string().describe("Unique identifier of the index"),
  value: z.string().describe("JSON value for the setting"),
},

src/tools/settings-tools.ts:228-250 (registration)

Registration loop that dynamically registers the update-filterable-attributes tool (along with others) using server.tool, including its specific endpoint 'filterable-attributes'.

updateSettingsTools.forEach(({ name, endpoint, description }) => {
  server.tool(
    name,
    description,
    {
      indexUid: z.string().describe("Unique identifier of the index"),
      value: z.string().describe("JSON value for the setting"),
    },
    async ({ indexUid, value }) => {
      try {
        // Parse the value string to ensure it's valid JSON
        const parsedValue = JSON.parse(value);
        
        const response = await apiClient.put(`/indexes/${indexUid}/settings/${endpoint}`, parsedValue);
        return {
          content: [{ type: "text", text: JSON.stringify(response.data, null, 2) }],
        };
      } catch (error) {
        return createErrorResponse(error);
      }
    }
  );
});

src/tools/settings-tools.ts:180-184 (registration)
Specific configuration object in updateSettingsTools array that defines the name, endpoint, and description for the tool.
```
{
  name: "update-filterable-attributes",
  endpoint: "filterable-attributes",
  description: "Update the filterable attributes setting",
},
```

Schema Changelog

Changes observed during successful MCP inspections.

First observedDec 10, 2025

TDQS

C2.1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. The description only states it's an update operation without explaining what 'update' means in this context - whether it replaces all filterable attributes, merges with existing ones, requires specific permissions, has side effects, or what the expected outcome is. For a mutation tool with zero annotation coverage, this is inadequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise - a single sentence with no wasted words. It's front-loaded with the essential action. While under-specified, what's present is efficiently structured without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what filterable attributes are, what format the 'value' parameter should be in beyond 'JSON value', what happens during the update, or what the tool returns. Given the complexity of updating a search index setting and the lack of structured documentation, the description should provide more context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both parameters (indexUid and value) having clear descriptions in the schema. The description doesn't add any meaningful information about parameters beyond what's already documented in the schema. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no parameter information in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Update the filterable attributes setting' is a tautology that essentially restates the tool name 'update-filterable-attributes'. It specifies the verb 'update' and resource 'filterable attributes setting', but lacks specificity about what filterable attributes are or what this operation actually does. It doesn't distinguish from sibling tools like 'reset-filterable-attributes' or 'get-filterable-attributes'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, when this should be used instead of resetting filterable attributes, or what happens to existing settings. With multiple sibling tools for managing filterable attributes (get, update, reset), the lack of differentiation is a significant gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server