SkillAgentSearch skills...

alfresco-mcp-sample

How to use Alfresco MCP Server in a sample project

Install / Use

claude mcp add aborroy -- npx -y github:aborroy/alfresco-mcp-sample

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

67/100

Category

Operations

Supported Platforms

Claude Code
Claude Desktop

Our assessment of alfresco-mcp-sample

alfresco-mcp-sample scores 67/100 on our quality scale, 707th of 762 Operations skills we index.

Its MCP Server is 2.7 KB long, well organised into 13 sections with 8 code examples: a solid amount of guidance for an agent.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
20/20
Description
8/15
Adoption
3/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-09-20 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 69/100, with 4 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

alfresco-mcp-sample compared with similar skills

All 4 of these similar skills score higher than alfresco-mcp-sample; compare them before choosing.

SkillScoreStarsUpdatedFormat
alfresco-mcp-sample (this skill)by aborroy6736mo agoMCP Server
Agent-Reachby Panniantong100101.1k2d agoCLAUDE.md
headroomby headroomlabs-ai10077.6ktodayCLAUDE.md
CowAgentby zhayujie10047.5ktodayCLAUDE.md
Scraplingby D4Vinci10089.3ktodayMCP Server

Frequently asked questions

How do I install alfresco-mcp-sample?
Run claude mcp add aborroy -- npx -y github:aborroy/alfresco-mcp-sample. The install tabs above show the steps for each supported agent.
Which AI agents does alfresco-mcp-sample work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is alfresco-mcp-sample safe to use?
It declares no license and scores 69/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is alfresco-mcp-sample still maintained?
The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

Alfresco MCP Sample

This project demonstrates how to use Alfresco MCP Server in a sample project:

  1. Run the Alfresco MCP Server
  2. Call it from a small Spring Boot agent
  3. Trigger that agent from ACA

Tested With

  • Alfresco MCP Server 1.1.0
    • Alfresco MCP Server image angelborroy/alfresco-mcp-server:1.1.0
  • Spring AI 1.1.4
  • Java 21
  • Docker Model Runner model ai/gpt-oss

Start Here

Prerequisites

  • Alfresco Content Services running at http://localhost:8080
  • Docker Desktop with Model Runner enabled
  • A model pulled in Model Runner:
docker model pull ai/gpt-oss

1. Configure the repo

cp .env.example .env

For the core demo, the default values are enough in most local setups.

2. Start the core services

docker compose up -d

This starts:

  • Phase 1: Alfresco MCP Server on http://localhost:8003/mcp
  • Phase 2: Summarization agent on http://localhost:8081
  • Phase 3: ACA extension on http://localhost:4200

3. Check the agent

curl http://localhost:8081/health

Expected response:

{"status":"ok","mcp_server":"http://host.docker.internal:8003/mcp","model":"ai/gpt-oss"}

4. Get an Alfresco ticket

curl -s -X POST http://localhost:8080/alfresco/api/-default-/public/authentication/versions/1/tickets \
  -H "Content-Type: application/json" \
  -d '{"userId": "admin", "password": "admin"}'

5. Summarize a document

curl -X POST http://localhost:8081/summarize/<nodeId> \
  -H "X-Alfresco-Ticket: TICKET_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

The agent:

  1. Calls get_pdf_rendition
  2. Extracts text with PDFBox
  3. Calls the LLM
  4. Writes the summary back with update_node_properties

6. Use the UI

Open http://localhost:4200 and use default credentials admin/admin

Choose action Summarize Description for a document, cm:description will be updated after a while with the summary.

Architecture

POST /summarize/{nodeId}
  -> Spring Boot agent
  -> MCP tool: get_pdf_rendition
  -> LLM summary
  -> MCP tool: update_node_properties

All Alfresco operations go through the MCP server. The agent does not call Alfresco REST directly.

Authentication

Tickets are passed at runtime:

  • HTTP clients send X-Alfresco-Ticket
  • The agent forwards that value as alf_ticket in each MCP tool call
  • MCP Inspector users pass alf_ticket directly in tool arguments

Tickets are not stored in .env.

Recommended Reading Order

Related Skills

View on GitHub
GitHub Stars3
CategoryOperations
Updated6mo ago
Forks0

Languages

JavaScript

Trust signals

69/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium3 low