Skip to main content
Glama
blockscout

Blockscout MCP Server

Official

inspect_contract_code

Read-only

Analyze verified smart contract source code and metadata on blockchain networks to understand contract functionality and structure.

Instructions

Inspects a verified contract's source code or metadata.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chain_idYesThe ID of the blockchain.
addressYesThe address of the smart contract.
file_nameNoThe name of the source file to inspect. If omitted, returns contract metadata and the list of source files.

Implementation Reference

  • The main handler function implementing the core logic of the 'inspect_contract_code' tool. It handles metadata retrieval or specific file fetching, progress reporting, validation, and response construction using shared helpers.
    @log_tool_invocation
    async def inspect_contract_code(
        chain_id: Annotated[str, Field(description="The ID of the blockchain.")],
        address: Annotated[str, Field(description="The address of the smart contract.")],
        file_name: Annotated[
            str | None,
            Field(
                description=(
                    "The name of the source file to inspect. "
                    "If omitted, returns contract metadata and the list of source files."
                ),
            ),
        ] = None,
        *,
        ctx: Context,
    ) -> ToolResponse[ContractMetadata | ContractSourceFile]:
        """Inspects a verified contract's source code or metadata."""
        if file_name is None:
            start_msg = f"Starting to fetch contract metadata for {address} on chain {chain_id}..."
        else:
            start_msg = f"Starting to fetch source code for '{file_name}' of contract {address} on chain {chain_id}..."
        await report_and_log_progress(
            ctx,
            progress=0.0,
            total=2.0,
            message=start_msg,
        )
    
        processed = await _fetch_and_process_contract(chain_id, address, ctx)
        if file_name is None:
            metadata = ContractMetadata.model_validate(processed.metadata)
            instructions = None
            notes = None
            if metadata.constructor_args_truncated:
                notes = ["Constructor arguments were truncated to limit context size."]
            if processed.source_files:
                instructions = [
                    (
                        "To retrieve a specific file's contents, call this tool again with the "
                        "'file_name' argument using one of the values from 'source_code_tree_structure'."
                    )
                ]
            return build_tool_response(data=metadata, instructions=instructions, notes=notes)
        if file_name not in processed.source_files:
            available = ", ".join(processed.source_files.keys())
            raise ValueError(
                f"File '{file_name}' not found in the source code for this contract. Available files: {available}"
            )
        return build_tool_response(data=ContractSourceFile(file_content=processed.source_files[file_name]))
  • Key helper function that fetches contract data from Blockscout API or cache, processes source files and metadata (including truncation), and returns a CachedContract object used by the handler.
    async def _fetch_and_process_contract(chain_id: str, address: str, ctx: Context) -> CachedContract:
        """Fetch contract data from cache or Blockscout API."""
    
        normalized_address = address.lower()
        cache_key = f"{chain_id}:{normalized_address}"
        if cached := await contract_cache.get(cache_key):
            return cached
    
        base_url = await get_blockscout_base_url(chain_id)
        await report_and_log_progress(
            ctx,
            progress=1.0,
            total=2.0,
            message="Resolved Blockscout instance URL.",
        )
        api_path = f"/api/v2/smart-contracts/{normalized_address}"
        raw_data = await make_blockscout_request(base_url=base_url, api_path=api_path)
        await report_and_log_progress(
            ctx,
            progress=2.0,
            total=2.0,
            message="Successfully fetched contract data.",
        )
        raw_data.setdefault("name", normalized_address)
        for key in [
            "language",
            "compiler_version",
            "verified_at",
            "optimization_enabled",
            "optimization_runs",
            "evm_version",
            "license_type",
            "proxy_type",
            "is_fully_verified",
            "decoded_constructor_args",
        ]:
            raw_data.setdefault(key, None)
    
        source_files: dict[str, str] = {}
        if raw_data.get("source_code"):
            if raw_data.get("additional_sources"):
                main_file_path = _determine_file_path(raw_data)
                source_files[main_file_path] = raw_data.get("source_code")
                for item in raw_data.get("additional_sources", []):
                    item_path = item.get("file_path")
                    if item_path:
                        source_files[item_path] = item.get("source_code")
            else:
                file_path = _determine_file_path(raw_data)
                source_files[file_path] = raw_data.get("source_code")
    
        # Create a copy to avoid mutating the original raw_data
        metadata_copy = raw_data.copy()
    
        # Process constructor args on the copy instead of the original
        from blockscout_mcp_server.tools.common import _truncate_constructor_args  # Local import to avoid cycles
    
        processed_args, truncated_flag = _truncate_constructor_args(metadata_copy.get("constructor_args"))
        metadata_copy["constructor_args"] = processed_args
        metadata_copy["constructor_args_truncated"] = truncated_flag
        if metadata_copy["decoded_constructor_args"]:
            processed_decoded, decoded_truncated = _truncate_constructor_args(metadata_copy["decoded_constructor_args"])
            metadata_copy["decoded_constructor_args"] = processed_decoded
            if decoded_truncated:
                metadata_copy["constructor_args_truncated"] = True
        metadata_copy["source_code_tree_structure"] = list(source_files.keys())
        for field in [
            "abi",
            "deployed_bytecode",
            "creation_bytecode",
            "source_code",
            "additional_sources",
            "file_path",
        ]:
            metadata_copy.pop(field, None)
    
        cached_contract = CachedContract(metadata=metadata_copy, source_files=source_files)
        await contract_cache.set(cache_key, cached_contract)
        return cached_contract
  • Pydantic models ContractMetadata (for metadata response) and ContractSourceFile (for file content response) defining the structured output schema for the tool. Used in ToolResponse[ContractMetadata | ContractSourceFile].
    class ContractMetadata(BaseModel):
        """Detailed metadata for a verified smart contract."""
    
        # Allow extra fields to preserve language-specific and contract-specific metadata
        # from Blockscout API that varies by verification status and contract type
        model_config = ConfigDict(extra="allow")
    
        name: str = Field(description="The name of the contract.")
        language: str | None = Field(description="The programming language of the contract (e.g., Solidity, Vyper).")
        compiler_version: str | None = Field(description="The compiler version used.")
        verified_at: str | None = Field(description="The timestamp when the contract was verified.")
        source_code_tree_structure: list[str] = Field(description="A list of all source file paths for the contract.")
    
        optimization_enabled: bool | None = Field(description="Flag indicating if compiler optimization was enabled.")
        optimization_runs: int | None = Field(description="The number of optimization runs.")
        evm_version: str | None = Field(description="The EVM version target.")
        license_type: str | None = Field(description="The license of the contract code (e.g., MIT, none).")
        proxy_type: str | None = Field(
            description="The type of proxy if the contract is a proxy (e.g., basic_implementation)."
        )
        is_fully_verified: bool | None = Field(description="Flag indicating if the contract is fully verified.")
    
        constructor_args: str | None = Field(description="The raw constructor arguments, possibly truncated.")
        decoded_constructor_args: str | dict | list | None = Field(
            default=None, description="Decoded constructor arguments, if available."
        )
        constructor_args_truncated: bool = Field(
            default=False, description="Indicates if constructor_args or decoded_constructor_args was truncated."
        )
    
    
    # --- Model for inspect_contract_code File Payload ---
    class ContractSourceFile(BaseModel):
        """Container for a single contract source file."""
    
        file_content: str = Field(description="The raw source code of the file.")
  • Registration of the 'inspect_contract_code' tool with the FastMCP server instance, including annotations for title, read-only hint, etc.
        structured_output=False,
        annotations=create_tool_annotations("Inspect Contract Code"),
    )(inspect_contract_code)
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, covering safety and scope. The description adds that it inspects 'verified contract's source code or metadata', which implies a read operation consistent with annotations, but doesn't provide additional behavioral context like rate limits, authentication needs, or what 'verified' entails.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose without unnecessary words. Every part of the sentence contributes directly to understanding the tool's function.

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

Completeness3/5

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

Given the 3 parameters with full schema coverage and annotations covering safety, the description is adequate but lacks output details (no output schema) and doesn't fully address sibling tool differentiation or usage context, leaving some gaps for an AI agent.

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 parameters are well-documented in the schema. The description mentions 'source code or metadata' and implies conditional behavior with 'file_name', adding some context, but doesn't provide extra semantic details beyond what the schema already covers.

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 ('inspects') and resource ('verified contract's source code or metadata'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_contract_abi' or 'read_contract', which might have overlapping functionality with smart contracts.

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 provides no guidance on when to use this tool versus alternatives like 'get_contract_abi' or 'read_contract'. It mentions the conditional behavior with 'file_name' but doesn't explain broader context or prerequisites for inspecting verified contracts.

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/blockscout/mcp-server'

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