PVZ Fusion MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@PVZ Fusion MCP ServerShow me the game rules for PVZ Fusion"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PVZ Fusion MCP Server
PVZ Fusion: Play, Wiki & Verified Build Guide
A Model Context Protocol server that exposes the canonical PVZ Fusion knowledge surface — game rules, modes, constraints, and entry points, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.
Official website: https://pvz-fusion.online
🎮 About PVZ Fusion
PVZ Fusion is an independent fan-made resource for exploring the game's gameplay, selected plant guides, and verified PC or Android build information. It is intended to help visitors understand the public resource and find the relevant live page before downloading anything.
The guide is a static site without a public API or database-backed service. This MCP exposes its documented rules, entry points, and source boundaries as read-only context; it does not run the game, host a build, or guarantee that a third-party download is safe or current.
PVZ Fusion is not an official PopCap, EA, or Plants vs. Zombies product. Use the live site, its source notes, and the applicable rights and download terms when following a link.
Related MCP server: Producer AI MCP Server
Tools
get_game_rules
Return the verified game rules, modes, constraints, and public entry points the site exposes. (PVZ Fusion)
Input: no parameters. Returns: text/markdown.
get_official_links
Return the canonical list of official links for PVZ Fusion (website, support, docs when available).
Input: no parameters. Returns: text/markdown.
Resources
site://pvz-fusion/rules— Verified game rules, modes, constraints, and public entry points.site://pvz-fusion/faq— Short FAQ generated from public site metadata.site://pvz-fusion/links— Canonical URLs to share with users.
Prompts
tell_me_about_pvz_fusion
Summarize what the site is, who it's for, and how it works. — PVZ Fusion
plan_a_run_pvz_fusion
Plan a single play-through using verified rules and entry points. — PVZ Fusion
Installation
Install via Smithery
npx -y @smithery/cli install pvz-fusion-mcp --client claude(Replace claude with cursor, windsurf, or continue for those clients.)
Install from source
git clone https://github.com/rocnubie/pvz-fusion-mcp.git
cd pvz-fusion-mcp
pnpm installThen add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):
{
"mcpServers": {
"pvz-fusion-mcp": {
"command": "node",
"args": [
"/absolute/path/to/pvz-fusion-mcp/src/index.mjs"
]
}
}
}Debug with MCP Inspector
npx @modelcontextprotocol/inspector node src/index.mjsOfficial Links
Website: https://pvz-fusion.online
Development
pnpm install
pnpm start # run the server over stdioLicense
MIT
Available Tools
2 toolsget_game_rulesA
Return the verified game rules, modes, constraints, and public entry points the site exposes. (PVZ Fusion)
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. Mentions 'verified' but does not disclose any behavioral traits such as rate limits, authentication needs, or output format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words. Front-loaded with action and resource. Parenthetical site tag adds context efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a zero-parameter tool with no output schema. Describes what is returned, but could optionally mention that the data is authoritative or static.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so schema coverage is effectively 100%. Description does not need to add parameter meaning, baseline score of 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it returns verified game rules, modes, constraints, and public entry points. Verb 'return' with specific resource. Differentiates from sibling 'get_official_links' by focus on rules.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like 'get_official_links'. No context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_official_linksA
Return the canonical list of official links for PVZ Fusion (website, support, docs when available).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses that the list is 'canonical' and 'when available', but lacks details on side effects, idempotency, or what happens if links are unavailable. The behavioral traits are minimally addressed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that communicates the essential purpose without extraneous words. It is front-loaded with the key action 'Return the canonical list'.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no parameters, the description reasonably compensates by specifying the content (official links, categorized as website, support, docs). It could be more precise about the return format (e.g., array of strings), but is sufficient for a simple list retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so schema description coverage is 100%. With no parameters, the description need not add any param meaning; a baseline score of 4 is appropriate since the tool requires no input and the description covers the purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'the canonical list of official links for PVZ Fusion' and specifies examples (website, support, docs), making the purpose explicit and distinct from the sibling tool 'get_game_rules' which likely returns game rules.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or limitations. While the sibling tool name hints at differentiation, no direct comparison or context for usage is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v0.1.0- First observed
get_game_rules - First observed
get_official_links
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: one returns game rules and modes, the other returns official links. There is no ambiguity between them.
Both tools follow the consistent verb_noun pattern (get_game_rules, get_official_links), which is clear and predictable.
With only 2 tools, the server feels thin for a game domain. While not extreme, it borders on insufficient scope for what would typically be expected.
The server lacks any gameplay-related tools (e.g., listing plants, starting a game, managing resources), making the surface severely incomplete for a game server.
Related MCP Connectors
- FlowdexOAuthdk.flowdex
Read and write your team's shared, AI-readable wiki from any MCP client.
Read-only MCP server for RZ AI Labs — query its services, workshops, and contact info.
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
Public, read-only MCP server for FarmNeural company facts, packages, and capabilities.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides verified game rules, official links, and FAQ for the 17-0 NFL roster strategy game to MCP-compatible AI clients.2MIT
- AlicenseAqualityCmaintenanceRead-only MCP server exposing Producer AI's music generation workflows, pricing, documentation, FAQ, and official links. Enables AI clients to retrieve product knowledge without requiring API keys.3MIT
- AlicenseAqualityCmaintenanceProvides read-only access to Pal Save Editor's workflow, safety boundaries, FAQ, and official links for MCP-compatible AI clients.2MIT
- AlicenseAqualityCmaintenanceRead-only MCP server exposing game rules, FAQs, and official links for the Women's World Cup 2027 simulator Pitch Queens, enabling AI clients to retrieve verified context without API keys.2MIT