Skip to main content
Glama
dewanshparashar

Arbitrum MCP Server

arbtrace_filter

Filter transaction traces on Arbitrum networks using specific criteria to analyze blockchain activity and debug smart contracts.

Instructions

Filter traces based on specified criteria (requires trace API)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rpcUrlNoThe RPC URL of the Arbitrum node (optional if default is set)
chainNameNoChain name (e.g., 'Xai', 'Arbitrum One') - will auto-resolve to RPC URL
filterYesFilter criteria for traces

Implementation Reference

  • MCP server tool handler for 'arbtrace_filter': resolves RPC URL using chain name or direct URL, creates NitroNodeClient instance, invokes traceFilter method with provided filter, and returns the result as formatted JSON text content.
    case "arbtrace_filter": {
      const rpcUrl = await this.resolveRpcUrl(
        (args.rpcUrl as string) || (args.chainName as string)
      );
      const nodeClient = new NitroNodeClient(rpcUrl);
      const result = await nodeClient.traceFilter(args.filter);
      return {
        content: [
          {
            type: "text",
            text: JSON.stringify(result, null, 2),
          },
        ],
      };
    }
  • src/index.ts:1378-1401 (registration)
    Tool registration in MCP server's getAvailableTools() method, including name, description, and inputSchema defining parameters: rpcUrl (optional), chainName (optional), filter (required object).
      name: "arbtrace_filter",
      description:
        "Filter traces based on specified criteria (requires trace API)",
      inputSchema: {
        type: "object" as const,
        properties: {
          rpcUrl: {
            type: "string",
            description:
              "The RPC URL of the Arbitrum node (optional if default is set)",
          },
          chainName: {
            type: "string",
            description:
              "Chain name (e.g., 'Xai', 'Arbitrum One') - will auto-resolve to RPC URL",
          },
          filter: {
            type: "object",
            description: "Filter criteria for traces",
          },
        },
        required: ["filter"],
      },
    },
  • NitroNodeClient helper method traceFilter that performs the actual RPC call to 'arbtrace_filter' with the filter parameter, handles errors, and returns TraceResult.
    async traceFilter(filter: any): Promise<TraceResult> {
      try {
        const traces = await this.makeRpcCall("arbtrace_filter", [filter]);
        return { traces };
      } catch (error) {
        return {
          traces: null,
          error: `Trace filter not supported on this RPC endpoint: ${
            (error as Error).message
          }`,
        };
      }
    }
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 of behavioral disclosure. It mentions 'requires trace API,' hinting at dependencies, but fails to describe what the tool does beyond filtering (e.g., output format, pagination, rate limits, or error handling). For a tool with no annotations, this leaves significant gaps in understanding its behavior.

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, efficient sentence that front-loads the core purpose. It avoids unnecessary words, though the parenthetical 'requires trace API' could be integrated more smoothly. Overall, it's appropriately sized with minimal waste.

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 no annotations, no output schema, and a tool that likely returns filtered trace data, the description is incomplete. It doesn't explain what the output looks like, how results are structured, or any limitations (e.g., max filters). For a filtering tool with nested parameters, more context is needed to guide effective use.

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%, so the schema fully documents the three parameters (rpcUrl, chainName, filter). The description adds no additional meaning beyond implying criteria-based filtering, which is already covered by the schema's 'filter' property description. This meets the baseline for high schema coverage without extra value.

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 clearly states the action ('Filter') and resource ('traces'), specifying it's based on criteria. It distinguishes from siblings like arbtrace_block or arbtrace_transaction by focusing on filtering rather than retrieving specific trace types. However, it doesn't explicitly differentiate from arbtrace_call or arbtrace_callMany, which might also involve filtering.

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 mentions 'requires trace API' as a prerequisite, which provides some context. However, it offers no guidance on when to use this tool versus alternatives like arbtrace_get or other trace-related siblings, nor does it specify scenarios where filtering is preferred over direct trace retrieval.

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/dewanshparashar/arbitrum-mcp'

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