add-mcp-resource
Add a new resource or resource template to an existing FastMCP server
Best use case
add-mcp-resource is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Add a new resource or resource template to an existing FastMCP server
Teams using add-mcp-resource should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/add-mcp-resource/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How add-mcp-resource Compares
| Feature / Agent | add-mcp-resource | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Add a new resource or resource template to an existing FastMCP server
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Add MCP Resource
Add a new resource or resource template to an existing FastMCP server.
## Usage
```bash
/add-mcp-resource [resource-uri]
```
## Arguments
- `[resource-uri]`: Optional - URI pattern for the resource (will prompt if not provided)
## Execution Instructions for Claude Code
When this command is run:
1. **Locate the FastMCP server** in the current project
2. **Determine resource type** (static or template)
3. **Gather resource requirements** through interactive questions
4. **Generate resource code** based on configuration
5. **Add resource to server** by modifying existing files
## Interactive Session Flow
### 1. Locate Server
```
Looking for FastMCP server...
Found: src/server.ts
Is this the correct server file? (yes/no):
```
### 2. Resource Type
```
What type of resource do you want to add?
1. Static resource - Fixed URI (e.g., "file:///config/settings.json")
2. Resource template - Dynamic URI with parameters (e.g., "user://{id}/profile")
Select (1-2):
```
### 3. Static Resource Configuration
For static resources:
```
Resource URI:
Example: "file:///logs/app.log", "config://settings", "docs://readme"
URI:
```
```
Resource name (human-readable):
Example: "Application Logs", "Server Configuration"
Name:
```
```
MIME type:
1. text/plain
2. application/json
3. text/markdown
4. text/html
5. Other (specify)
Select (1-5):
```
```
Description (optional):
```
### 4. Resource Template Configuration
For resource templates:
```
URI template pattern:
Use {parameter} syntax for dynamic parts.
Examples:
- "file:///logs/{name}.log"
- "user://{userId}/profile"
- "docs://{category}/{page}"
URI template:
```
```
Resource name:
Example: "User Profiles", "Log Files"
Name:
```
```
Let's define the template parameters.
Parameter: {name}
Description:
Required? (yes/no):
Add auto-completion? (yes/no):
```
If auto-completion:
```
How should auto-completion work?
1. Static list of values
2. Dynamic lookup (I'll implement)
3. Prefix matching (e.g., "Ex" -> "Example")
Select (1-3):
```
### 5. Content Type
```
What type of content does this resource return?
1. Text content
2. Binary content (base64 blob)
3. Multiple items (array of content)
Select (1-3):
```
### 6. Data Source
```
Where does the resource data come from?
1. File system
2. Database
3. External API
4. In-memory/computed
5. Other
Select (1-5):
```
## Generated Code Examples
### Static Resource (Text)
```typescript
server.addResource({
uri: "{{uri}}",
name: "{{name}}",
mimeType: "{{mimeType}}",
description: "{{description}}",
async load() {
// TODO: Implement data loading
const content = await readFile("path/to/file");
return {
text: content,
};
},
});
```
### Static Resource (Binary)
```typescript
server.addResource({
uri: "{{uri}}",
name: "{{name}}",
mimeType: "{{mimeType}}",
async load() {
// TODO: Load binary data
const buffer = await readFile("path/to/file");
return {
blob: buffer.toString("base64"),
};
},
});
```
### Static Resource (Multiple Items)
```typescript
server.addResource({
uri: "{{uri}}",
name: "{{name}}",
mimeType: "{{mimeType}}",
async load() {
// Return multiple content items
return [
{ text: "First section content" },
{ text: "Second section content" },
{ text: "Third section content" },
];
},
});
```
### Resource Template (Basic)
```typescript
server.addResourceTemplate({
uriTemplate: "{{uriTemplate}}",
name: "{{name}}",
mimeType: "{{mimeType}}",
arguments: [
{{#each parameters}}
{
name: "{{name}}",
description: "{{description}}",
required: {{required}},
},
{{/each}}
],
async load(args) {
const { {{parameterNames}} } = args;
// TODO: Load resource based on parameters
return {
text: `Content for ${JSON.stringify(args)}`,
};
},
});
```
### Resource Template with Auto-Completion (Static)
```typescript
server.addResourceTemplate({
uriTemplate: "{{uriTemplate}}",
name: "{{name}}",
mimeType: "text/plain",
arguments: [
{
name: "{{paramName}}",
description: "{{paramDescription}}",
required: true,
complete: async (value) => {
// Static list of completions
const options = ["option1", "option2", "option3"];
const filtered = options.filter(opt =>
opt.toLowerCase().includes(value.toLowerCase())
);
return { values: filtered };
},
},
],
async load(args) {
return {
text: `Content for ${args.{{paramName}}}`,
};
},
});
```
### Resource Template with Dynamic Completion
```typescript
server.addResourceTemplate({
uriTemplate: "{{uriTemplate}}",
name: "{{name}}",
mimeType: "application/json",
arguments: [
{
name: "{{paramName}}",
description: "{{paramDescription}}",
required: true,
complete: async (value) => {
// Dynamic lookup from database/API
const results = await searchItems(value);
return {
values: results.map(r => r.name),
};
},
},
],
async load(args) {
const item = await findItem(args.{{paramName}});
if (!item) {
return { text: "Not found" };
}
return {
text: JSON.stringify(item, null, 2),
};
},
});
```
### Resource from File System
```typescript
import { readFile } from "fs/promises";
import { join } from "path";
server.addResourceTemplate({
uriTemplate: "file:///logs/{name}.log",
name: "Log Files",
mimeType: "text/plain",
arguments: [
{
name: "name",
description: "Name of the log file",
required: true,
complete: async (value) => {
// List available log files
const files = await readdir("/var/logs");
const logFiles = files
.filter(f => f.endsWith(".log"))
.map(f => f.replace(".log", ""));
return {
values: logFiles.filter(f => f.includes(value)),
};
},
},
],
async load(args) {
const filePath = join("/var/logs", `${args.name}.log`);
const content = await readFile(filePath, "utf-8");
return { text: content };
},
});
```
### Resource from Database
```typescript
server.addResourceTemplate({
uriTemplate: "user://{userId}/profile",
name: "User Profiles",
mimeType: "application/json",
arguments: [
{
name: "userId",
description: "User ID",
required: true,
},
],
async load(args) {
const user = await db.users.findById(args.userId);
if (!user) {
return { text: JSON.stringify({ error: "User not found" }) };
}
return {
text: JSON.stringify({
id: user.id,
name: user.name,
email: user.email,
createdAt: user.createdAt,
}, null, 2),
};
},
});
```
### Resource from External API
```typescript
server.addResourceTemplate({
uriTemplate: "weather://{city}",
name: "Weather Data",
mimeType: "application/json",
arguments: [
{
name: "city",
description: "City name",
required: true,
},
],
async load(args) {
const response = await fetch(
`https://api.weather.example/v1/${encodeURIComponent(args.city)}`
);
if (!response.ok) {
return { text: JSON.stringify({ error: "City not found" }) };
}
const data = await response.json();
return {
text: JSON.stringify(data, null, 2),
};
},
});
```
## File Placement
```
Where should the resource code be added?
1. Inline in server.ts
2. New file in resources/ directory
3. Existing resources file
Select (1-3):
```
## Implementation Notes
1. **Find existing server**: Locate FastMCP server files
2. **Check for resources directory**: Create if needed
3. **Generate imports**: Add necessary imports
4. **Insert code**: Add resource at appropriate location
5. **Match style**: Preserve existing code formatting
6. **Summary**: Show generated resource and URI patternRelated Skills
zod
Zod schema validation patterns and type inference. Auto-loads when validating schemas, parsing data, validating forms, checking types at runtime, or using z.object/z.string/z.infer in TypeScript.
typescript-import-style
Merge-friendly import formatting (one-per-line, alphabetical). Auto-loads when writing TypeScript/JavaScript imports to minimize merge conflicts in parallel development. Enforces consistent grouping and sorting.
setup-mcp-auth
Configure authentication for an existing FastMCP server
fastmcp
FastMCP TypeScript framework patterns for MCP servers. Auto-loads when building MCP servers, creating tools/resources/prompts, implementing authentication, configuring transports, or working with FastMCP in TypeScript.
add-mcp-tool
Add a new tool to an existing FastMCP server with guided configuration
plan-with-team
Validate plan file ownership
privacy-compliance
GDPR, CCPA, and privacy compliance guidance for data protection. Use when handling personal data, implementing consent management, or ensuring regulatory compliance across jurisdictions.
oauth
OAuth 2.0 and OpenID Connect implementation patterns. Use when implementing authentication, authorization flows, or integrating with OAuth providers like Google, GitHub, or custom identity providers.
mcp-security
Use when securing MCP servers, preventing prompt injection, implementing authorization, validating user input, or building secure multi-agent pipelines. Provides 5-layer defense architecture patterns.
rag-cag-security
Security patterns for RAG and CAG systems with multi-tenant isolation. Use when building retrieval-augmented or cache-augmented generation systems that require tenant isolation, access control, and secure data handling.
chunking-strategies
Document chunking strategies for RAG systems. Use when implementing document processing pipelines to determine optimal chunking approaches based on document type and retrieval requirements.
review-django-commands
Review Django management commands for proper structure and refactor if needed