Skip to main content
Glama

update_mcp_server

Idempotent

Update selected fields of an existing MCP server while preserving omitted settings; configuration, connection, authentication, or transport changes refresh its tool availability.

Instructions

Update only supplied MCP server fields. config replaces the whole object; send all settings to retain. Changes invalidate the agent tool surface; connection, configuration, authentication and transport changes also invalidate server tool discovery.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "mcp_server_id": "<mcp_server_id>"
    },
    "name": "update_mcp_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoNew name
configNoNew configuration
statusNoNew status
endpointNoNew endpoint
transportNoNew transport type
auth_methodNoNew authentication method; OAuth is not yet supported for this external-server configuration
descriptionNoNew description
mcp_server_idYesMCP server UUID
integration_idNoRegistered integration link; see list_integrations. With tunnel authentication, destination access requires an active grant. For other methods, the link is informational. Omit to preserve the current link.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv2.2.4
    • changedInput schema / properties / auth_method / description
      Previous value: -"Novo método de autenticação (oauth ainda não disponível)"New value: +"New authentication method; OAuth is not yet supported for this external-server configuration"
    • changedInput schema / properties / config / description
      Previous value: -"Nova configuração"New value: +"New configuration"
    • changedInput schema / properties / description / description
      Previous value: -"Nova descrição"New value: +"New description"
    • changedInput schema / properties / endpoint / description
      Previous value: -"Novo endpoint"New value: +"New endpoint"
    • addedInput schema / properties / integration_id
      Added value: +{
      +  "description": "Registered integration link; see list_integrations. With tunnel authentication, destination access requires an active grant. For other methods, the link is informational. Omit to preserve the current link.",
      +  "format": "uuid",
      +  "type": "string"
      +}
    • changedInput schema / properties / mcp_server_id / description
      Previous value: -"UUID do MCP server"New value: +"MCP server UUID"
    • changedInput schema / properties / name / description
      Previous value: -"Novo nome"New value: +"New name"
    • changedInput schema / properties / status / description
      Previous value: -"Novo status"New value: +"New status"
    • changedInput schema / properties / transport / description
      Previous value: -"Novo tipo de transporte"New value: +"New transport type"
  2. Changed2 schema fields changedv2.2.3
    • changedInput schema / properties / auth_method / description
      Previous value: -"Novo método de autenticação"New value: +"Novo método de autenticação (oauth ainda não disponível)"
    • changedInput schema / properties / auth_method / enum
      Previous value: -[
      -  "none",
      -  "bearer",
      -  "api_key",
      -  "tunnel",
      -  "oauth"
      -]New value: +[
      +  "none",
      +  "bearer",
      +  "api_key",
      +  "tunnel"
      +]
  3. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-destructive, idempotent. The description adds real context beyond them: patch semantics, whole-object replacement for config, and the consequence that changes invalidate the agent tool surface and, for connection/auth/transport changes, invalidate server tool discovery. Missing only details like whether the response echoes the updated server.

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

Conciseness4/5

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

Two sentences, front-loaded with the partial-update contract before the side-effect warning. The second sentence is dense and jargon-heavy ("invalidate the agent tool surface") but every clause carries distinct information, so little is wasted.

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

Completeness4/5

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

For a 9-parameter mutation tool with full schema coverage and no output schema, the definition covers the semantics an agent most needs: what is changed, how config is replaced, and what side effects follow. Gaps are minor — no mention of validation failures, name uniqueness, or response shape.

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

Parameters4/5

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

Schema description coverage is 100%, so baseline is 3; the description earns an extra point by explaining replacement semantics for config, something the schema's "New configuration" does not convey. It does not touch the other eight parameters, leaving their meaning entirely to the schema.

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

Purpose4/5

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

States a specific verb and resource ("Update ... MCP server fields") and immediately clarifies that it is a partial update ("only supplied ... fields"), which separates it from a full-replace or create operation. It does not name a sibling, but update vs. create/delete/get is unambiguous from the name alone.

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

Usage Guidelines3/5

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

Useful field-level guidance is given — "config replaces the whole object; send all settings to retain" tells the agent exactly how to behave for that parameter. However, there is no explicit when-to-use/when-not routing (e.g., when to prefer create_mcp_server or test_mcp_server), so usage is implied rather than stated.

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

Deploy Server

Other Tools