Skip to main content
Glama
Sign In
BunkerWeb MCP

BunkerWeb MCP

Official
by bunkerity
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

create_service

Create a BunkerWeb service from a server name with optional unprefixed settings and a draft flag. Fails if the name is taken; changes are saved to the database and applied later by the scheduler.

Instructions

Create a service named by SERVER_NAME (first word becomes its ID) with optional unprefixed settings and a draft flag. Fails if the name or a server name is taken. Use update_service to change one. Saved to the database; the scheduler applies it later; this tool cannot confirm it is live.

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": {
      "server_name": "<server_name>"
    },
    "name": "create_service"
  }
}

Input Schema

NameRequiredDescriptionDefault
is_draftNoCreate as an unpublished draft
variablesNoUnprefixed per-service setting names and values, e.g. {"USE_MODSECURITY": "yes"}
server_nameYesServer name; its first word becomes the service ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.7.0
    • changedInput schema / properties / is_draft / description
      Previous value: -"Create as draft"New value: +"Create as an unpublished draft"
    • changedInput schema / properties / server_name / description
      Previous value: -"Primary server name"New value: +"Server name; its first word becomes the service ID"
    • changedInput schema / properties / variables / description
      Previous value: -"Service variables"New value: +"Unprefixed per-service setting names and values, e.g. {\"USE_MODSECURITY\": \"yes\"}"
  2. Changed3 schema fields changedv0.5.0
    • addedInput schema / properties / is_draft / description
      Added value: +"Create as draft"
    • addedInput schema / properties / server_name / description
      Added value: +"Primary server name"
    • addedInput schema / properties / variables / description
      Added value: +"Service variables"
  3. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the name-collision failure mode ("Fails if the name or a server name is taken"), that the write is persisted to the database only, that the scheduler applies it asynchronously, and that liveness cannot be confirmed. This eventual-consistency caveat is exactly the non-obvious behavior an agent needs before verifying results.

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?

Three tight sentences, front-loaded with the create action and naming rule, followed by failure behavior and the update_service alternative. The semicolon-chained phrasing ("Saved to the database; the scheduler applies it later") is compressed but readable and earns its space.

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?

With no output schema, the description carries the burden of describing the result, and it does: the object is persisted, applied later, and cannot be confirmed live. Nothing critical is missing for a non-destructive create, though it could note the returned identifier explicitly.

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%, so all three parameters are already documented, and the description largely restates them ("unprefixed settings and a draft flag") rather than adding new semantics. The ID-derivation detail is also present in the schema's server_name description, so the added value over structured data is minimal — baseline 3.

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?

States a specific verb and resource ("Create a service") and immediately pins down the naming derivation ("first word becomes its ID"), so an agent knows exactly what the call produces. It also names the sibling it is not ("Use update_service to change one"), making differentiation explicit.

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?

Explicitly routes mutation of an existing service to update_service, which is the main ambiguity for an agent in this tool family. It does not spell out preconditions (e.g., whether the target instance must exist or be reachable), which keeps it short of a 5.

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