What is jahia-mcp-community-server CLAUDE.md?

Project instructions for a Jahia module that exposes Jahia's GraphQL API, an interface for querying application data, through MCP, a standard way for AI clients to call tools. It also describes the module's Java source layout, access checks, and stored instruction documents called skills.

Working on the Jahia MCP community server, including its servlet, GraphQL integration, API-token checks, path whitelist, and dynamically stored skills.

It gives Claude Code the project context needed to understand the server's architecture, permissions, tools, and source files.

How Jahia/jahia-mcp-community-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Jahia/jahia-mcp-community-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Jahia/jahia-mcp-community-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Jahia/jahia-mcp-community-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jahia/jahia-mcp-community-server/claude-md/github.svg)](https://agentmods.dev/instructions/jahia/jahia-mcp-community-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jahia/jahia-mcp-community-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jahia/jahia-mcp-community-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jahia/jahia-mcp-community-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jahia/jahia-mcp-community-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,180 This file is loaded in full into every session.

When invoked 6,180 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.06180	$0.06180
Opus 5.5	$0.02472	$0.02472
Sonnet 5.5	$0.01236	$0.01236
Haiku 4.5	$0.00618	$0.00618

Measured today against content hash ccb92682f836, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jahia-mcp-community-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Jahia MCP Community Server

What this module does

An extension of Jahia's mcp-server module (0.5.x). This module is version 2.x. It contributes four MCP tools to the mcp-server endpoint (/modules/mcp) through its public tool SPI: community.graphql.execute, community.graphql.introspect, community.skill.list and community.skill.get. The module owns no endpoint and no MCP SDK: mcp-server handles transport, authentication, JSON-RPC and the tool catalog.

Every community tool is administrator-only. community.graphql.execute is additionally gated by a whitelist that is read-only by default (queries allowed except under admin, mutations and subscriptions refused). Read-only is not non-sensitive: every other query returns what the administrator can read (JCR-stored settings such as the mail server configuration, user data) to the AI client, so the docs recommend an explicit allow list in production. Skills (Markdown instruction documents) are stored in JCR.

Source layout

src/main/java/org/jahia/community/mcp/
    McpSkillService.java                   # DS component (root package): JCR CRUD and seeding of mcp:skill nodes
    access/
        CommunityMcpAccess.java            # Administrator gate (JCR 'admin' on /) and bound-caller lookup
        GraphQLWhitelistGate.java          # Operation-qualified whitelist gate (graphql-java parser, AST walk)
    config/
        McpConfigService.java              # DS component, configurationPolicy=REQUIRE, metatype (ocd Config)
        WhitelistEntries.java              # Entry syntax: query:<path> / mutation:<path>; legacy = query-only
        WhitelistSnapshot.java             # Immutable snapshot published atomically by McpConfigService
    tools/
        AbstractCommunityTool.java         # Template: final execute() = audit(adminGate(doExecute))
        AbstractSkillTool.java             # Read-only skill tools, tags reads-ugc
        GraphQLExecuteTool.java            # community.graphql.execute    (DESTRUCTIVE)
        GraphQLIntrospectTool.java         # community.graphql.introspect (READ_ONLY)
        SkillListTool.java                 # community.skill.list        (READ_ONLY)
        SkillGetTool.java                  # community.skill.get         (READ_ONLY)
        InternalGraphQLClient.java         # In-process call of OsgiGraphQLHttpServlet, bounded response
        ToolSupport.java                   # Schema loading, audit recording, hashing, sanitizing
    graphql/                               # ONLY exported package (Export-Package)
        McpGraphQLExtensionsProvider.java  # DXGraphQLExtensionsProvider (bundle-scan registration)
        McpQueryExtension.java             # Adds `communityMcp` to Query  → CommunityMcpQuery
        McpQuery.java                      # settings, skills; types CommunityMcpSettings, CommunityMcpSkill
        McpMutationExtension.java          # Adds `communityMcp` to Mutation → CommunityMcpMutation
        McpMutation.java                   # saveSettings, saveSkill, deleteSkill

src/main/resources/
    schemas/community.*.json               # Hand-written JSON Schemas (draft 2020-12), one per tool
    META-INF/definitions.cnd               # mcp:skill node type; mcpmix:mcp (droppable, hidden from pickers)
    META-INF/configurations/org.jahia.community.mcp.cfg   # Default whitelist (empty); first line is fixed
    skills/default/*.md                    # Default skills, seeded into JCR when absent
    javascript/locales/{en,fr}.json        # Admin UI strings

src/javascript/CommunityMcpConfig/         # React admin UI (allow-list tree, save bar, confirmations)
tests/                                     # Cypress Docker integration tests (provision mcp-server)

Read the full file on GitHub · 340 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +1 lines · +28 tokens per session ccb92682f836
yesterday Changed · +146 lines · +3,525 tokens per session 61e0ae49c03c
2mo ago First seen · 193 lines · 2,627 tokens per session scan A 6d2880b691b3

Subscribe to this mod's changes

jahia-mcp-community-server CLAUDE.md is an instructions file published in the GitHub repository Jahia/jahia-mcp-community-server (0 stars, last pushed today), licensed MIT. It adds 6,180 tokens to every session, about $0.0247 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs Building agents community jahia-team-support

jahia-mcp-community-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
jahia-mcp-community-server CLAUDE.mdJahia/jahia-mcp-community-server	Instructions file	0	today	MIT	A	6,180	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

jahia-mcp-community-server: Instructions file for Claude Code