Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@eRegulations MCP Server list all available procedures"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server implementation for accessing eRegulations API data. This server provides structured, AI-friendly access to eRegulations instances, making it easier for AI models to answer user questions about administrative procedures.
Access eRegulations data through a standardized protocol
Query procedures, steps, requirements, and costs
MCP prompt templates to guide LLM tool usage
Streamlined implementation using standard I/O connections
Related MCP server: Federal Register MCP Server
The easiest way to install and run the eRegulations MCP Server is through Smithery:
Visit https://smithery.ai/server/@unctad-ai/eregulations-mcp-server for the installation command.
You can also run the eRegulations MCP Server directly using npx with the published npm package:
# Set environment variables and run with npx
export EREGULATIONS_API_URL=https://example.com/api && export NODE_ENV=production && npx -y @unctad-ai/eregulations-mcp-server@latestThe server can be configured using command-line arguments (preferred) or environment variables:
--api-url: URL of the eRegulations API to connect to
EREGULATIONS_API_URL: URL of the eRegulations API to connect to (fallback if --api-url is not provided)
Note: Command-line arguments take precedence over environment variables.
The MCP server provides the following tools:
listProceduresLists all available procedures in the eRegulations system.
getProcedureDetailsGets detailed information about a specific procedure by its ID.
Parameters:
procedureId: ID of the procedure to retrieve
getProcedureStepGets information about a specific step within a procedure.
Parameters:
procedureId: ID of the procedure
stepId: ID of the step within the procedure
The server provides prompt templates to guide LLMs in using the available tools correctly. These templates explain the proper format and parameters for each tool. LLM clients that support the MCP prompt templates capability will automatically receive these templates to improve their ability to work with the API.
# Run in development mode
npm run start
# Run tests
npm test
# Run tests with watch mode
npm run test:watch
# Run test client
npm run test-clientGet detailed information about a specific procedure by ID.
| Name | Required | Description | Default |
|---|---|---|---|
| procedureId | Yes | ID of the procedure to retrieve |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only states 'Get detailed information' without mentioning error cases, access requirements, or what differentiates 'detailed' from other procedure endpoints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single front-loaded sentence with no redundant content. It immediately communicates the operation without unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-param retrieval tool, the description covers the core intent, but with no output schema or annotations, it does not explain what 'detailed information' includes or how it differs from getProcedureStep. More context would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with procedureId described as 'ID of the procedure to retrieve'. The description's 'by ID' adds no further meaning or constraints beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') and resource ('detailed information about a specific procedure by ID'), clearly distinguishing it from sibling tools: listProcedures (which lists all) and getProcedureStep (which targets a single step).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when/when-not guidance or alternative mentions. The phrase 'a specific procedure' implies this is for targeted retrieval, not listing, but that is implicit rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get information about a specific step within a procedure.
| Name | Required | Description | Default |
|---|---|---|---|
| stepId | Yes | ID of the step within the procedure | |
| procedureId | Yes | ID of the procedure |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states 'Get information', implying a read operation, but does not describe what information is returned, whether there are any side effects, permissions, or error conditions. This is minimal and lacks behavioral context beyond the verb.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no redundant words. It is front-loaded and immediately conveys the tool's purpose, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read operation with two well-specified parameters, the description is adequate but not complete. There is no output schema, so the description should have explained the return format or what information is included for the step. It also lacks usage guidance and behavioral details, leaving some context gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameters are fully documented. The description does not add meaning beyond the schema, but since the schema already explains 'procedureId' and 'stepId', the baseline of 3 applies. No additional parameter semantics are provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves information about a specific step within a procedure, distinguishing it from the sibling tools listProcedures (which lists procedures) and getProcedureDetails (which likely gets procedure-level info). It uses the specific verb 'get' and identifies the resource precisely, though it does not explicitly name alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It does not mention context such as 'use this when you need step-level details' or exclude cases. With sibling tools available, the lack of usage guidance is a clear gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all available procedures in the eRegulations system.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 discloses that the tool lists 'all' procedures, implying no filtering or pagination. However, it does not mention return format, ordering, or any read-only guarantees. For a simple list operation, this is acceptable but not rich in behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that states exactly what the tool does with no extraneous words. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (no parameters, no output schema), the description is nearly complete. It clearly states scope ('all available'). A minor gap is that it doesn't explicitly note that the result can be used with sibling tools for details, but this is a slight enhancement rather than a necessity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema fully documents that there is nothing to configure. The baseline for 0-parameter tools is 4 per guidelines. The description adds no parameter-specific semantics because none are needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: 'List all available procedures' in the 'eRegulations system.' The use of 'all' distinguishes this from sibling tools that target specific procedures (getProcedureDetails, getProcedureStep). The verb 'list' is precise and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies its use case: when you need an overview of all procedures. However, it does not explicitly mention when to use alternatives or exclude cases (e.g., 'for details on a single procedure, use getProcedureDetails'). The guidance is not misleading, but it is implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0getProcedureDetailsgetProcedureSteplistProceduresEach tool has a distinct purpose: listing all procedures, retrieving a specific procedure's details, and getting a specific step within a procedure. There is no overlap or confusion between these operations.
All tool names follow a consistent camelCase verb_noun pattern: listProcedures, getProcedureDetails, getProcedureStep. The naming is uniform and predictable.
Three tools is slightly on the lower end but reasonable for a focused read-only procedures lookup server. Each tool serves a clear purpose, and the count is not thin enough to feel incomplete.
The server covers the essential read operations for procedures and steps. A minor gap is the lack of a search or list steps function, but the core lookup workflow is supported.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
US Federal Register for AI agents: rules, notices, executive orders, agency lookup. No keys.
US Federal Register for AI agents: rules, notices, executive orders, agency lookup. No keys.
Search and trace US federal rules across the Federal Register, eCFR, and Regulations.gov.
Resolve any government entity worldwide and submit service requests. Open civic data for AI agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mcpflow/eregulations-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
