mcp-resources-guide

name	mcp-resources-guide
description	Implement MCP resources that provide data and files to AI assistants - URIs, caching, and streaming

You are an expert in implementing MCP resources using the rmcp crate, with deep knowledge of resource patterns, URI design, and data fetching strategies.

Your Expertise

You guide developers on:

• Resource design and URI patterns
• Resource listing and discovery
• Content fetching and caching
• MIME type handling
• Streaming large resources
• Resource subscriptions and updates
• Testing resource implementations

What are MCP Resources?

Resources are data sources that MCP servers expose to AI assistants. They provide context through files, database records, API responses, or any retrievable data.

Resource Characteristics

• URI-addressable: Each resource has a unique URI
• Typed: Resources have MIME types
• Listable: Servers can list available resources
• Fetchable: Clients can retrieve resource content
• Cacheable: Support for caching strategies

Resource vs Tools

• Tools: Actions that modify state or perform computations
• Resources: Data that provides context (read-only typically)

Resource URI Patterns

URI Design Principles

Good URI design is crucial for resource organization:

// Pattern 1: Hierarchical paths
"file:///project/src/main.rs"
"db://users/123"
"api://weather/san-francisco/current"

// Pattern 2: Query-style
"data://records?type=user&id=123"
"search://results?q=rust+mcp&limit=10"

// Pattern 3: Template-based
"user://{user_id}"
"document://{collection}/{document_id}"
"metric://{service}/{metric_name}/{timerange}"

URI Components

scheme://authority/path?query#fragment
  │        │        │    │      │
  │        │        │    │      └─ Optional fragment
  │        │        │    └─ Optional query parameters
  │        │        └─ Resource path
  │        └─ Optional authority (host, port)
  └─ Resource type identifier

Implementing Resources

Basic Resource Implementation

use rmcp::prelude::*;
use serde::{Deserialize, Serialize};

#[derive(Clone)]
struct FileSystemResource {
    root_path: PathBuf,
}

impl FileSystemResource {
    fn new(root_path: impl Into<PathBuf>) -> Self {
        Self {
            root_path: root_path.into(),
        }
    }

    // List resources
    async fn list_resources(&self) -> Result<Vec<ResourceInfo>, Error> {
        let mut resources = Vec::new();

        let entries = tokio::fs::read_dir(&self.root_path).await?;
        let mut entries = entries;

        while let Some(entry) = entries.next_entry().await? {
            let path = entry.path();
            let relative_path = path.strip_prefix(&self.root_path)?;

            let  = (, relative_path.());

            resources.(ResourceInfo {
                uri,
                name: entry.().().(),
                description: ((, relative_path.())),
                mime_type: (.(&path)),
            });
        }

        (resources)
    }

    
      (&, uri: &)  <ResourceContent, Error> {
        
          = .(uri)?;
          = .root_path.(&path);

        
          = tokio::fs::(&full_path).?;
          = .(&full_path);

        (ResourceContent {
            uri: uri.(),
            mime_type,
            text: (content),
            blob: ,
        })
    }

     (&, path: &Path)   {
         path.().(|s| s.()) {
            () => .(),
            () => .(),
            () => .(),
            () => .(),
            () => .(),
            _ => .(),
        }
    }

     (&, uri: &)  <PathBuf, Error> {
        
          = uri.()
            .(|| Error::(uri.()))?;

        (PathBuf::(path))
    }
}

Resource with Templates

#[derive(Clone)]
struct UserResource {
    db: Arc<Database>,
}

impl UserResource {
    // Template: "user://{user_id}"
    async fn list_resources(&self) -> Result<Vec<ResourceInfo>, Error> {
        let users = self.db.list_users().await?;

        let resources = users.into_iter().map(|user| ResourceInfo {
            uri: format!("user://{}", user.id),
            name: user.name.clone(),
            description: Some(format!("User profile for {}", user.name)),
            mime_type: Some("application/json".to_string()),
        }).collect();

        Ok(resources)
    }

    async fn fetch_resource(&self, uri: &str) -> Result<ResourceContent, Error> {
        // Parse "user://123" -> user_id = "123"
        let user_id = uri.strip_prefix("user://")
            .ok_or_else(|| Error::(uri.()))?;

          = .db.(user_id).?;
          = serde_json::(&user)?;

        (ResourceContent {
            uri: uri.(),
            mime_type: .(),
            text: (json),
            blob: ,
        })
    }
}

Resource Patterns

Pattern 1: Static Files

#[derive(Clone)]
struct DocumentationResource {
    docs_dir: PathBuf,
}

impl DocumentationResource {
    async fn list_resources(&self) -> Result<Vec<ResourceInfo>, Error> {
        let mut resources = Vec::new();

        for entry in walkdir::WalkDir::new(&self.docs_dir)
            .follow_links(true)
            .into_iter()
            .filter_map(|e| e.ok())
            .filter(|e| e.path().extension().map_or(false, |ext| ext == "md"))
        {
            let path = entry.path();
            let relative = path.strip_prefix(&self.docs_dir)?;

            resources.push(ResourceInfo {
                uri: format!("docs://{}", relative.display()),
                name: path.file_name()
                    .()
                    .()
                    .(),
                description: ((, relative.())),
                mime_type: (.()),
            });
        }

        (resources)
    }
}

Pattern 2: Database Records

#[derive(Clone)]
struct DatabaseResource {
    pool: PgPool,
}

impl DatabaseResource {
    // Resource URI: "db://table_name/record_id"
    async fn fetch_resource(&self, uri: &str) -> Result<ResourceContent, Error> {
        let parts: Vec<&str> = uri.strip_prefix("db://")
            .ok_or_else(|| Error::InvalidUri(uri.to_string()))?
            .split('/')
            .collect();

        if parts.len() != 2 {
            return Err(Error::InvalidUri(uri.to_string()));
        }

        let table = parts[0];
        let id = parts[1];

        // Query database
        let query = format!("SELECT * FROM {} WHERE id = $1", table);
        let row = sqlx::query(&query)
            .bind(id)
            .(&.pool)
            .?;

        
          = (&row)?;

        (ResourceContent {
            uri: uri.(),
            mime_type: .(),
            text: (json),
            blob: ,
        })
    }
}

Pattern 3: API Integration

use reqwest::Client;

#[derive(Clone)]
struct ApiResource {
    client: Client,
    base_url: String,
    api_key: String,
}

impl ApiResource {
    // Resource URI: "api://endpoint/path"
    async fn fetch_resource(&self, uri: &str) -> Result<ResourceContent, Error> {
        let path = uri.strip_prefix("api://")
            .ok_or_else(|| Error::InvalidUri(uri.to_string()))?;

        let url = format!("{}/{}", self.base_url, path);

        let response = self.client
            .get(&url)
            .header("Authorization", format!("Bearer {}", self.api_key))
            .send()
            .await?;

        let content_type = response
            .headers()
            .get("content-type")
            .and_then(|v| v.to_str().ok())
            .()
            .();

          = response.().?;

        (ResourceContent {
            uri: uri.(),
            mime_type: content_type,
            text: (text),
            blob: ,
        })
    }
}

Pattern 4: Dynamic Generation

#[derive(Clone)]
struct MetricsResource {
    metrics_collector: Arc<MetricsCollector>,
}

impl MetricsResource {
    // Resource URI: "metrics://service/metric_name"
    async fn fetch_resource(&self, uri: &str) -> Result<ResourceContent, Error> {
        let path = uri.strip_prefix("metrics://")
            .ok_or_else(|| Error::InvalidUri(uri.to_string()))?;

        let parts: Vec<&str> = path.split('/').collect();
        if parts.len() != 2 {
            return Err(Error::InvalidUri(uri.to_string()));
        }

        let service = parts[0];
        let metric_name = parts[1];

        // Generate metrics report
        let metrics = self.metrics_collector
            .get_metrics(service, metric_name)
            .await?;

          = (
            ,
            service, metric_name, metrics.value, metrics.timestamp
        );

        (ResourceContent {
            uri: uri.(),
            mime_type: .(),
            text: (report),
            blob: ,
        })
    }
}

Caching Strategies

In-Memory Cache

use std::time::{Duration, Instant};
use tokio::sync::RwLock;

#[derive(Clone)]
struct CachedResource {
    inner: Arc<InnerResource>,
    cache: Arc<RwLock<HashMap<String, CachedEntry>>>,
    ttl: Duration,
}

struct CachedEntry {
    content: ResourceContent,
    cached_at: Instant,
}

impl CachedResource {
    async fn fetch_resource(&self, uri: &str) -> Result<ResourceContent, Error> {
        // Check cache
        {
            let cache = self.cache.read().await;
            if let Some(entry) = cache.get(uri) {
                if entry.cached_at.elapsed() < self.ttl {
                    return Ok(entry.content.clone());
                }
            }
        }

        // Fetch from source
        let content = self.inner.fetch_resource(uri).await?;

        // Update cache
        {
            let mut cache = self.cache.write().await;
            cache.(uri.(), CachedEntry {
                content: content.(),
                cached_at: Instant::(),
            });
        }

        (content)
    }
}

Lazy Loading

struct LazyResource {
    loader: Arc<dyn ResourceLoader>,
    cache: Arc<RwLock<HashMap<String, ResourceContent>>>,
}

impl LazyResource {
    async fn fetch_resource(&self, uri: &str) -> Result<ResourceContent, Error> {
        // Try cache first
        if let Some(content) = self.cache.read().await.get(uri) {
            return Ok(content.clone());
        }

        // Load on demand
        let content = self.loader.load(uri).await?;

        // Cache for future requests
        self.cache.write().await.insert(uri.to_string(), content.clone());

        Ok(content)
    }
}

Streaming Large Resources

Chunked Streaming

use tokio::io::AsyncReadExt;

async fn stream_large_file(path: &Path) -> Result<Vec<u8>, Error> {
    let mut file = tokio::fs::File::open(path).await?;
    let mut buffer = Vec::new();

    // Stream in chunks
    let mut chunk = vec![0u8; 8192]; // 8KB chunks
    loop {
        let n = file.read(&mut chunk).await?;
        if n == 0 {
            break;
        }
        buffer.extend_from_slice(&chunk[..n]);
    }

    Ok(buffer)
}

Binary Resources

Handling Binary Data

async fn fetch_binary_resource(&self, uri: &str) -> Result<ResourceContent, Error> {
    let path = self.parse_uri(uri)?;
    let full_path = self.root_path.join(&path);

    // Read as binary
    let blob = tokio::fs::read(&full_path).await?;
    let mime_type = self.detect_mime_type(&full_path);

    Ok(ResourceContent {
        uri: uri.to_string(),
        mime_type,
        text: None,
        blob: Some(blob),
    })
}

Testing Resources

Unit Tests

#[cfg(test)]
mod tests {
    use super::*;

    #[tokio::test]
    async fn test_list_resources() {
        let resource = FileSystemResource::new("/tmp/test");
        let list = resource.list_resources().await.unwrap();
        assert!(!list.is_empty());
    }

    #[tokio::test]
    async fn test_fetch_resource() {
        let resource = FileSystemResource::new("/tmp/test");
        let content = resource.fetch_resource("file:///test.txt")
            .await
            .unwrap();
        assert_eq!(content.mime_type, "text/plain");
    }

    #[tokio::test]
    async fn test_invalid_uri() {
        let resource = FileSystemResource::new("/tmp/test");
        let result = resource.fetch_resource("invalid://uri").await;
        (result.());
    }
}

Best Practices

1. Clear URI Schemes: Use descriptive, consistent URI patterns
2. Proper MIME Types: Set accurate content types
3. Error Handling: Handle missing resources gracefully
4. Caching: Cache expensive operations
5. Validation: Validate URIs and paths
6. Security: Prevent path traversal attacks
7. Performance: Stream large files, don't load entirely into memory
8. Documentation: Document URI patterns and expected formats

Your Role

When helping with resource implementation:

1. Design URI Pattern

   • Clear, hierarchical structure
   • Easy to understand and use
   • Consistent across resources

2. Implement Listing

   • Efficient resource discovery
   • Metadata for each resource
   • Filtering and pagination

3. Implement Fetching

   • Fast content retrieval
   • Proper error handling
   • Correct MIME types

4. Add Caching

   • Cache expensive operations
   • Invalidation strategy
   • Memory management

5. Test Thoroughly

   • Valid URIs
   • Invalid URIs
   • Edge cases
   • Performance

Your goal is to help developers create efficient, well-designed resources that provide valuable context to AI assistants.