mcp-1panel-plus

Overview Schema Source Related Servers Discussions Admin

Create or Update Website Reverse-Proxy Rule

upsert_website_proxy

Create or edit a website's reverse-proxy location rule, with sanitized upstream URL, match path, and headers to block Nginx directive injection.

Instructions

Create (operate: "create") or edit (operate: "edit") a reverse-proxy location rule on a website. Sanitizes upstream URL, match path, and headers against Nginx directive injection.

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": {
      "website_id": "<website_id>",
      "operate": "<operate>",
      "name": "<name>",
      "proxy_pass": "<proxy_pass>"
    },
    "name": "upsert_website_proxy"
  }
}

Input Schema

Name	Required	Description	Default
`sni`	No	Enable TLS SNI when proxying to an HTTPS upstream.
`name`	Yes	Unique proxy rule name on this website (e.g. "root" or "api").
`cache`	No	Enable proxy response caching.
`match`	No	Location match path starting with "/" (defaults to "/").	/
`enable`	No	Whether the proxy rule is active.
`nodeId`	No	Target node ID: "local" for the Main Node, or a numeric string ID (e.g. "3") from list_nodes.	local
`operate`	Yes	Operation mode: "create" a new rule or "edit" an existing named rule.
`modifier`	No	Nginx location modifier (defaults to "^~").	^~
`replaces`	No	Optional sub_filter string replacements map.
`cache_time`	No	Cache duration when `cache` is true.
`cache_unit`	No	Cache duration unit.
`proxy_host`	No	Upstream Host header value (defaults to "$host").	$host
`proxy_pass`	Yes	Upstream target URL (e.g. "http://127.0.0.1:3000" or "https://backend.example.com").
`ssl_verify`	No	Verify upstream TLS certificate when using HTTPS proxy_pass.
`website_id`	Yes	Numeric website ID.
`proxy_ssl_name`	No	Optional TLS SNI server name when `sni` is true.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 11, 2026

TDQS

B3.4/5.0

Behavior3/5

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

With annotations already declaring readOnlyHint=false, destructiveHint=false, and openWorldHint=true, the description adds real value by disclosing that upstream URL, match path, and headers are sanitized against Nginx directive injection. However, it does not explain edit semantics (whether omitted fields are reset to defaults), permission requirements, or failure behavior for invalid upstreams.

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 short sentences, front-loaded with the operation and resource, with no filler. The inline enum callouts make the create/edit distinction scannable without opening the schema.

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

Completeness3/5

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

For a 16-parameter mutation tool with a nested `replaces` object and no output schema, the description is quite sparse. The rich schema and annotations compensate for most of it, but upsert semantics (what an `edit` does to unspecified fields, what is returned) are left unexplained.

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% across all 16 parameters, so the schema carries the semantics; the description only re-states the meaning of `operate`. The sanitization note hints that `proxy_pass`, `match`, and header-related inputs are validated, but adds no format or constraint detail beyond 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?

The description names a specific verb pair (create/edit) and resource ('a reverse-proxy location rule on a website') and maps each verb to the `operate` enum values. An agent can tell this is the write-side counterpart to `list_website_proxies` and `delete_website_proxy`, though the siblings are not named explicitly.

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?

It distinguishes create vs edit via the `operate` values, which is genuinely useful routing information. It gives no guidance on when to prefer this over alternatives such as `delete_website_proxy`, nor any prerequisites (site existence, rule name collisions on create).

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