Skip to main content
Glama
RSS3-Network

RSS3 MCP Server

Official
by RSS3-Network

API-getRSSActivityByPath

Retrieve RSS activity data from decentralized chains and social platforms using a specific path query. This tool accesses the RSS3 network to fetch activity information through the MCP server interface.

Instructions

Retrieve RSS Activity by Path

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Generic execution handler for all dynamically generated API tools, including "API-getRSSActivityByPath". Looks up the OpenAPI operation by tool name and executes it via the associated HttpClient.
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
    	// console.error("call tool", request.params);
    	const { name, arguments: params } = request.params;
    
    	console.error("name", name);
    
    	if (name === "API-get-input-schema") {
    		for (const mcpToolWithClient of mcpToolWithClients) {
    			for (const [toolName, def] of Object.entries(
    				mcpToolWithClient.mcpTools.tools,
    			)) {
    				for (const method of def.methods) {
    					const toolNameWithMethod = `${toolName}-${method.name}`;
    					const truncatedToolName = toolNameWithMethod.slice(0, 64);
    					if (truncatedToolName === params.toolName) {
    						return {
    							content: [
    								{ type: "text", text: JSON.stringify(method.inputSchema) },
    							],
    						};
    					}
    				}
    			}
    		}
    		throw new Error(`Method ${params.toolName} not found`);
    	}
    
    	// find operation
    	const mcpToolWithClient = mcpToolWithClients.find(
    		(t) => t.mcpTools.openApiLookup[name],
    	);
    	if (!mcpToolWithClient) {
    		throw new Error(`Method ${name} not found`);
    	}
    
    	const operation = mcpToolWithClient.mcpTools.openApiLookup[name];
    
    	// execute
    	try {
    		const response = await mcpToolWithClient.client.executeOperation(
    			operation,
    			params,
    		);
    		return {
    			content: [
    				{
    					type: "text", // currently this is the only type that seems to be used by mcp server
    					text: JSON.stringify(response.data), // TODO: pass through the http status code text?
    				},
    			],
    		};
    	} catch (error) {
    		console.error("Error in tool call", error);
    		if (error instanceof HttpClientError) {
    			console.error(
    				"HttpClientError encountered, returning structured error",
    				error,
    			);
    			const data = error.data?.response?.data ?? error.data ?? {};
    			return {
    				content: [
    					{
    						type: "text",
    						text: JSON.stringify({
    							status: "error", // TODO: get this from http status code?
    							...(typeof data === "object" ? data : { data: data }),
    						}),
    					},
    				],
    			};
    		}
    		throw error;
    	}
    });
  • index.js:100-147 (registration)
    Dynamically lists all available tools generated from OpenAPI specs. Constructs tool names as `${toolName}-${method.name}` (truncated), which includes "API-getRSSActivityByPath" if present in the RSS3 OpenAPI.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
    	console.error("list tools");
    	/**
    	 * @typedef {import("@modelcontextprotocol/sdk/types.js").Tool} Tool
    	 * @type {Tool[]}
    	 */
    	const tools = [];
    
    	for (const mcpToolWithClient of mcpToolWithClients) {
    		for (const [toolName, def] of Object.entries(
    			mcpToolWithClient.mcpTools.tools,
    		)) {
    			for (const method of def.methods) {
    				console.error("method", method);
    				const toolNameWithMethod = `${toolName}-${method.name}`;
    				const truncatedToolName = toolNameWithMethod.slice(0, 64);
    				const trimmedDescription = method.description.split("Error")[0].trim();
    				tools.push({
    					name: truncatedToolName,
    					description: trimmedDescription,
    					inputSchema: {
    						type: "object",
    						properties: {},
    					},
    				});
    			}
    		}
    	}
    
    	tools.unshift({
    		name: "API-get-input-schema",
    		description:
    			"Get the input schema for a given API. We should always use this tool to get the input schema for a given API before calling the API.",
    		inputSchema: {
    			type: "object",
    			properties: {
    				toolName: {
    					type: "string",
    					description: "The name of the tool to get the input schema for",
    				},
    			},
    		},
    	});
    
    	console.error("tools", tools);
    
    	return { tools };
    });
  • Special tool to retrieve the exact input schema for any dynamic API tool, such as "API-getRSSActivityByPath", by looking up the corresponding OpenAPI method schema.
    if (name === "API-get-input-schema") {
    	for (const mcpToolWithClient of mcpToolWithClients) {
    		for (const [toolName, def] of Object.entries(
    			mcpToolWithClient.mcpTools.tools,
    		)) {
    			for (const method of def.methods) {
    				const toolNameWithMethod = `${toolName}-${method.name}`;
    				const truncatedToolName = toolNameWithMethod.slice(0, 64);
    				if (truncatedToolName === params.toolName) {
    					return {
    						content: [
    							{ type: "text", text: JSON.stringify(method.inputSchema) },
    						],
    					};
    				}
    			}
    		}
    	}
    	throw new Error(`Method ${params.toolName} not found`);
    }
  • Converts OpenAPI specifications to MCP tool definitions and associates HttpClient instances. This generates the tool structures, including for "API-getRSSActivityByPath".
    const mcpToolWithClients = converterWithClients.map((cwc) => {
    	const mcpTools = cwc.converter.convertToMCPTools();
    	return {
    		mcpTools,
    		client: cwc.client,
    	};
    });
  • Fetches RSS3 OpenAPI specifications from gi.rss3.io and ai.rss3.io, which contain the endpoint definitions like getRSSActivityByPath used to generate the MCP tool.
    const openApiSpecs = (
    	await Promise.allSettled([
    		fetch("https://gi.rss3.io/docs/openapi.json").then(async (res) => {
    			if (!res.ok) throw new Error(`HTTP error! status: ${res.status}`);
    			return res.json();
    		}),
    		fetch("https://ai.rss3.io/openapi.json").then(async (res) => {
    			if (!res.ok) throw new Error(`HTTP error! status: ${res.status}`);
    			return res.json();
    		}),
    	]).then((results) => {
    		return results.map((result) => {
    			if (result.status === "fulfilled") {
    				const client = new HttpClient(
    					{
    						baseUrl: result.value.servers[0].url,
    					},
    					result.value,
    				);
    				return {
    					spec: result.value,
    					client,
    				};
    			}
    
    			console.error("Failed to fetch openapi spec", result.reason);
    			return null;
    		});
    	})
    ).filter(Boolean);
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It states 'Retrieve' implying a read-only operation, but doesn't disclose behavioral traits such as authentication needs, rate limits, error handling, or what 'by Path' means in practice. This leaves significant gaps for a tool with no structured safety hints.

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?

The description is a single, front-loaded sentence with no wasted words, making it efficient. However, it's overly terse and could benefit from more context given the lack of annotations and sibling differentiation.

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

Completeness2/5

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

Given the complexity implied by 'RSS Activity' and the lack of annotations and output schema, the description is incomplete. It doesn't explain what 'RSS Activity' is, what 'by Path' means, or what the return values might be, leaving the agent with insufficient information for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add parameter details, but since there are no parameters, this is acceptable. Baseline is 4 as per rules for 0 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Retrieve RSS Activity by Path' clearly states the action (retrieve) and resource (RSS Activity by Path), but it's vague about what 'RSS Activity' entails and doesn't distinguish it from sibling tools like 'API-getActivityById' or 'API-getFederatedActivityById', which also retrieve activities. It provides a basic purpose but lacks specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance on when to use this tool versus alternatives. With siblings like 'API-getActivityById' and 'API-getFederatedActivityById', it's unclear if this tool is for a specific type of activity or context, leaving the agent without usage context.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RSS3-Network/mcp-server-rss3'

If you have feedback or need assistance with the MCP directory API, please join our Discord server