Skip to main content
Glama
astandrik

Local YDB MCP

by astandrik
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

local_ydb_restart_stack

Restart a local YDB profile after static compatibility preflight, recreating configured containers in order and restoring unexpected ones. Use confirm=true to execute; omit for a plan-only preview.

Instructions

Reconcile and restart the selected profile after inventory and a full check-only static compatibility preflight. Before stopping any container, require the existing static container to match the profile image, network, data mount, environment, restart policy, healthcheck, and exact loopback bindings for static gRPC, monitoring, and every configured dynamic gRPC port; configured binding changes require destroy followed by bootstrap. Then report missing configured and unexpected one-off dynamic containers, stop running dynamic containers before static, unconditionally recreate every configured node in index order including containers observed restarting, require each exact Docker container to be stably running plus registered by IC port, and restore only previously running unexpected containers without removing them. Because removed configured definitions cannot be recovered from inventory, rollback uses restart or bootstrap reconciliation. Without confirm=true this returns the restart plan only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
confirmNoMust be true to execute planned commands. Omit or false for plan-only output.
profileNoNamed profile from local-ydb.config.json. Defaults to config.defaultProfile.
configPathNoAbsolute path to an explicit local-ydb config file. Missing, unreadable, oversized, or invalid explicit files fail closed instead of using defaults.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.21
    • changedInput schema / properties / configPath / description
      Previous value: -"Explicit local-ydb config file path to load for this tool call. Useful when the MCP server should pick up a different config without restart."New value: +"Absolute path to an explicit local-ydb config file. Missing, unreadable, oversized, or invalid explicit files fail closed instead of using defaults."
    • addedInput schema / properties / configPath / minLength
      Added value: +1
  2. Addedv0.1.12
  3. Removedv0.1.12
  4. Addedv0.1.5
  5. Removedv0.1.4
  6. Changed3 schema fields changedv0.1.1
    • changedInput schema / properties / configPath / description
      Previous value: -"Explicit local-ydb config file path to load for this tool call."New value: +"Explicit local-ydb config file path to load for this tool call. Useful when the MCP server should pick up a different config without restart."
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to execute commands. Omit or false for plan-only output."New value: +"Must be true to execute planned commands. Omit or false for plan-only output."
    • addedInput schema / properties / profile / description
      Added value: +"Named profile from local-ydb.config.json. Defaults to config.defaultProfile."
  7. First observedv0.1.0

TDQS

A4.2/5.0
Behavior5/5

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

The description goes far beyond the annotations by detailing the preflight compatibility checks, ordering guarantees (stop dynamic before static, recreate in index order), unconditional recreation of configured nodes, restoration of previously running unexpected containers, and the irrecoverable nature of removed definitions. It also explains the plan-only behavior without confirm. No contradiction with annotations is present.

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

Conciseness3/5

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

The description is front-loaded with the primary purpose, but it is a single dense, run-on paragraph with many interdependent clauses. The information is valuable, but the structure is hard to parse quickly and could benefit from bullet points or shorter sentences. It is more verbose than necessary for an agent to extract the key behavioral contract.

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?

Given the tool's complexity and the absence of an output schema, the description covers the major behavioral expectations: preflight checks, container ordering, plan-only mode, and rollback constraints. It does not explicitly describe the success output when confirm=true is passed, but the plan-only output is specified and the operational flow is otherwise well covered.

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 coverage is 100%, so the parameters are already fully documented. The description adds context about the profile being 'selected' and that confirm=true gates execution, but it does not materially add meaning beyond what the schema already states. The baseline of 3 applies because the schema does the heavy lifting.

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

Purpose5/5

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

The description opens with a specific verb and resource: 'Reconcile and restart the selected profile.' It clearly differentiates this from siblings by describing plan-only behavior and the boundary with destroy-then-bootstrap for binding changes, so an agent can distinguish it from bootstrap, destroy_stack, or status tools.

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

Usage Guidelines4/5

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

The description clearly states that bindings changes require destroy followed by bootstrap rather than restart, which is an explicit exclusion. It also implies use when reconciling a running stack after inventory, and says confirm=true is required for execution. It does not explicitly name alternative sibling tools for the main use case, but the conditions and exclusions are concrete enough.

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