EGIPCI MCP Server
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., "@EGIPCI MCP Serverlook up archaeological site 12345"
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.
EGIPCI MCP Server
MCP (Model Context Protocol) server for querying archaeological site information from the EGIPCI service (Expedient d'Informació del Patrimoni Cultural Immoble) of the Department of Culture of the Generalitat de Catalunya.
This server allows AI editors like Claude Code, Cursor, and other MCP clients to access archaeological information from Catalunya through the standard MCP protocol.
Note: This package is designed to be used as an MCP server through npx, not as a global installation.
Quick Start
This package is designed as an MCP server - no installation needed! Just configure it in your MCP client.
Related MCP server: Met Museum MCP Server
Usage
MCP Client Configuration
To use this server with an MCP client, add the following configuration to your mcp.json file:
{
"mcpServers": {
"gencat-egipci": {
"command": "npx",
"args": ["-y", "@d0whc3r/egipci-mcp@latest"],
"env": {
"EGIPCI_COOKIE": "your_intranet_cookie_value_here"
}
}
}
}Available Tools
query_egipci_site
Query information for a specific archaeological site.
Parameters:
cookie(string, optional):.intranetcookie for EGIPCI authentication. If not provided, theEGIPCI_COOKIEenvironment variable will be usedid(string, required): Archaeological site ID to query
Usage example:
With cookie as parameter:
{
"name": "query_egipci_site",
"arguments": {
"cookie": "your_intranet_cookie_value",
"id": "12345"
}
}With cookie from environment variable:
{
"name": "query_egipci_site",
"arguments": {
"id": "12345"
}
}Response: Returns the site information in XML format as provided by the EGIPCI service.
Authentication Methods
Using Environment Variable (Recommended)
The safest and most convenient way is to configure the cookie in the EGIPCI_COOKIE environment variable in the MCP configuration. This has several advantages:
Security: The cookie is not exposed in each tool call
Convenience: You don't need to pass the cookie in each query
Reusability: Single configuration for all queries
Maintenance: Easy update when the cookie expires
Using Cookie Parameter
You can also pass the cookie directly as a parameter in each call. This is useful for:
Using different cookies for different queries
Cases where you cannot configure environment variables
Testing and development
Obtaining Authentication Cookie
To obtain the required .intranet cookie:
Go to https://egipci.cultura.gencat.cat/ in your browser
Log in with your credentials
Open developer tools (F12)
Go to the "Application" or "Storage" tab
In "Cookies", look for the
.intranetcookieCopy the cookie value to use as parameter
Error Handling
The server handles various types of errors using the got library:
Missing or invalid parameters: Input validation with Zod
HTTP errors: Status codes 4xx/5xx using
got.HTTPErrorNetwork errors: Connectivity issues using
got.RequestErrorAuthentication errors: Invalid or expired cookie
Format errors: XML response validation
All errors are returned with descriptive messages.
Development
For contributors and developers working on this project:
Development Setup: See
.kiro/steering/tech.mdfor technology stack and commandsTesting Guidelines: See
.kiro/steering/testing.mdfor testing patterns and requirementsCI/CD Pipeline: See
.kiro/steering/pipeline.mdfor deployment and quality gatesProject Structure: See
.kiro/steering/structure.mdfor architecture details
Requirements
Valid
.intranetcookie for EGIPCI authenticationFor development: Node.js >= 18.0.0, pnpm
Available Tools
1 toolquery_egipci_siteQuery EGIPCI for an archaeological site infoB
Query archaeological site information from the EGIPCI service of the Generalitat de Catalunya
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The archaeological site ID to query | |
| cookie | No | The .intranet cookie for EGIPCI authentication (optional if EGIPCI_COOKIE env var is set) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose behavioral traits such as read-only access, authentication requirements, or response size. Since there are no annotations, the description carries the burden, and it fails to explain the effect or safety of the call.
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, concise sentence with no redundant words. It directly states the tool's purpose.
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 no output schema and no sibling tools, the description is adequate but lacks information about return value structure, authentication details, and error scenarios. It meets minimum viability but has clear 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 schema fully documents both parameters. The description adds no extra meaning beyond what is in the schema, which is acceptable but not enhanced.
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 it queries archaeological site information from the EGIPCI service. It uses a specific verb and resource, but could be more precise by mentioning it requires a site ID and returns details.
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 guidance is provided on when to use this tool or alternatives. There are no sibling tools, but the description does not clarify prerequisites (e.g., authentication via cookie) or typical scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v1.2.1- First observed
query_egipci_site
TDQS
Only one tool exists, so there is no possibility of confusion or overlap.
The single tool name follows a clear verb_noun pattern (query_egipci_site), establishing a consistent convention.
With only one tool for what likely requires multiple operations (e.g., query, list, detail), the surface feels insufficient for a well-scoped server.
The server provides only a query capability; without create, update, or delete tools, it is incomplete for typical archaeological site management.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
- UnifAPIOAuthcom.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- AlicenseBqualityCmaintenanceAn MCP server that enables AI models to retrieve information from Ragie's knowledge base through a simple 'retrieve' tool.13291MIT
- AlicenseAqualityCmaintenanceA MCP Server that lets user ask AI models to discover the collection of the Metropolitan Museum of Art. Adds the discovered art works as Resources on the server.42,26433MIT
- AlicenseAqualityDmaintenanceAn MCP server that enables AI-powered exploration of RDF data and SPARQL querying via RDF4J. It provides tools for executing queries, searching knowledge graph resources, and retrieving schema summaries.131MIT
- AlicenseAqualityDmaintenanceMCP server for querying Spanish government open data APIs including grants, legislation, company registry, statistics, and open data catalog. Enables LLMs to access Spanish public information on-the-fly.265MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/d0whc3r/egipci-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server