How to connect Claude to ECI JobBOSS2
Short answer
Connect Claude to JobBOSS2 by running a Model Context Protocol server next to the SQL Server database that exposes a few read-only tools, then adding it as a connector. For data that cannot leave your network, use an open-weight model instead of Claude.
Claude is good at long-document reasoning and careful, structured work, which fits job shop tasks such as reading a 30-page customer spec against your routing, or summarising a quarter of job cost variances. What it lacks, out of the box, is any knowledge of what is in your JobBOSS2 database.
The standard bridge is MCP, the Model Context Protocol. An MCP server describes a handful of tools, and a Claude client (Claude Desktop, Claude Code, or an app you build on the API) can call them. Your JobBOSS2 data stays where it is until a specific tool call returns specific rows.
This page covers how to set that up, the deployment choices for Claude itself, and where the line falls for regulated work.
What teams use it for
Spec versus routing review
Provide a customer PO and drawing notes and have Claude compare them to the quoted routing and material in JobBOSS2, flagging mismatches before the job releases.
Quarterly variance narrative
Claude pulls closed-job cost data through a tool and writes a plain-language explanation of where actual hours diverged from estimates.
Order desk questions
Staff ask about order status, ship dates or inventory through Claude Desktop instead of navigating screens.
Quote preparation assistant
Claude finds comparable past jobs through a search tool and drafts a quote worksheet with assumptions listed.
Customer corrective action draft
From a returned job and its operations history, Claude drafts the factual timeline for an 8D or corrective action response for a quality manager to complete.
ECI JobBOSS2 integration surface
- Microsoft SQL Server database: create read-only views and a dedicated login. Typical underlying tables include Job, Job_Operation, Material_Req, Delivery, PO_Header and Quote, with names varying by version.
- JobBOSS2 API, if included in your edition, can back the same tools. Confirm available resources and auth with ECI.
- An MCP server can be written with the official SDKs (TypeScript or Python) and exposed over stdio for a single desktop or over HTTP for a team.
- Report exports (Excel, CSV, PDF) remain useful as a fallback input for ad hoc analysis in Claude without any connector.
How it works
- 1
Decide the Claude deployment
Options include Claude apps with a team or enterprise plan, the Anthropic API, or Claude through AWS Bedrock or Google Vertex AI if your IT already standardises on those clouds.
- 2
Build the MCP server
Define tools like get_job, list_open_jobs, get_material_status and search_quotes. Each should have a typed schema and a hard row cap.
- 3
Connect it to SQL views
Use a read-only login scoped to views. Parameterise every query, never concatenate model-provided text into SQL.
- 4
Register as a connector
For desktop use, add the server in the client configuration. For teams, host it over HTTPS with authentication and register it as a remote connector.
- 5
Write tool descriptions carefully
The descriptions are what Claude reads to decide when to call each tool. Say what the tool returns, units, and what it cannot do.
- 6
Test with real questions
Run 30 questions your staff actually ask. Check answers against the application screens before widening access.
Example flows
Pre-release spec check
Trigger: A planner is about to release a new job for a repeat customer.
- The planner attaches the new PO text to Claude.
- Claude calls get_job and get_routing for the quoted job.
- It compares material grade, finish and quantity to the PO.
- It lists differences and asks the planner to confirm each.
Result: Catches spec drift before material is cut.
Month-end margin story
Trigger: The controller asks why margin dropped in the month.
- Claude calls a closed-jobs cost tool for the month and the prior month.
- It groups variances by customer and operation.
- It writes a one-page summary with the supporting job numbers.
Result: A draft narrative the controller edits, with traceable numbers.
Keeping data on-prem
Claude is a hosted model, so a fully air-gapped JobBOSS2 shop cannot run it locally. The practical split is this: keep the MCP server and database on your network, and decide per data class what may reach a hosted model. Where ITAR, CUI or strict customer NDAs apply, the same MCP-style tool layer can sit in front of an open-weight model served on your own GPUs, so the architecture is reusable. Shops often use hosted Claude for non-sensitive work and the private model for job and drawing data.
Security checklist
- Review the provider's data handling terms for your plan, including retention and training exclusions, before connecting any customer data.
- Read-only database login, scoped to views, with parameterised queries only.
- Authenticate HTTP MCP servers and map each user to a JobBOSS2-aligned role so people only see what they should.
- Cap rows returned and log every tool call with user and parameters.
- Treat text inside job notes and customer attachments as untrusted, since it can contain instructions aimed at the model.
Ways to get it done
Exports into Claude
Effort: Hours
Quick wins for analysis and writing with no integration work.
Build your own MCP server
Effort: 2 to 6 weeks
Good for a shop with a developer. Straightforward for read tools, careful work for access control.
Netray or another partner
Effort: A few weeks for a pilot
When you want hosted and on-prem model options behind the same tool layer, plus someone to evaluate answer quality.
Pitfalls
- !Giving the MCP server a broad SQL login 'just to test' and never tightening it.
- !Vague tool descriptions, leading Claude to pick the wrong tool or invent parameters.
- !Letting job note fields flow into the model unfiltered, which opens prompt injection from attachments or vendor text.
- !Assuming all users should see all customers. JobBOSS2 roles do not automatically carry over to your MCP server.
- !Skipping a legal check on cloud processing of controlled technical data.
Frequently asked questions
Does ECI provide an official Claude connector for JobBOSS2?
We are not aware of one that you can rely on, and offerings change, so ask ECI or your reseller. A custom MCP server over read-only SQL views is a practical alternative that works on most on-prem installs.
Which Claude deployment is best for a manufacturer?
It depends on your existing cloud. Teams already on AWS may prefer Bedrock, Google shops may prefer Vertex, and others use the Anthropic API or Claude plans directly. The MCP server you build is largely the same across them.
Can Claude run on-prem against JobBOSS2?
No, Claude is accessed as a hosted service. For on-prem needs, reuse the same tool layer with an open-weight model running on your own hardware.
Is MCP better than a custom API for this?
MCP is a standard way for different AI clients to discover and call tools, so you build once and can use Claude, other assistants and agents. A plain REST API works too but needs a separate adapter per client.
Can Claude change data in JobBOSS2?
Not unless you build write tools, and we recommend against it at first. Start with read tools and drafts, then add a narrow, approved write path later if the value is clear.
Want Claude working on your ECI JobBOSS2?
A free 30 minute assessment: we map the integration path for your version and setup, and where it should run.
Get a free assessmentTry it here, free
JobBOSS to E2 Shop System Migration Checklist
A practical checklist for moving a small shop from JobBOSS to E2 Shop System, from data audit through cutover and first month close. Works in reverse too.
Keep exploring
Free tools
- JobBOSS to E2 Shop System Migration ChecklistA practical checklist for moving a small shop from JobBOSS to E2 Shop System, from data audit through cutover and first month close. Works in reverse too.
- Claude Desktop MCP Config JSON GeneratorBuild the mcpServers entry for claude_desktop_config.json with the right command, arguments and environment variables.
- JobBOSS Classic AI Assistant Sizing and Value CalculatorEstimate peak concurrency, GPU count, index size, hours saved and payback for a private AI assistant on JobBOSS Classic.
ERP fixes and how-tos
- JobBOSS2 API: Documentation, Keys and Integration OptionsWhat integration options JobBOSS and JobBOSS2 offer: API access, SQL reads, reports and file exchange, how to get access, and how to connect apps or AI safely.
- JobBOSS and QuickBooks Online Integration: What Works and What to CheckHow JobBOSS and JobBOSS2 work with QuickBooks Online and Desktop: what syncs, what does not, the options, and when a job shop outgrows QuickBooks.
- How to Create Custom Reports in JobBOSS and JobBOSS2Create and customise reports in JobBOSS and JobBOSS2: report designer basics, common shop reports, parameters and SQL-based alternatives.
AI on your ERP
- AI for JobBOSS2 quoting and schedulingHow AI helps JobBOSS2 job shops quote from past job actuals and explain scheduling conflicts, with read-only access and private hosting options.
- AI for JobBOSS2 in Precision Machining: Quotes, Routings and Job Cost Answers from Your Own DataPrivate AI for JobBOSS2 precision machine shops: quote history, routing actuals, job cost variance and on-time delivery answers, kept on your own network.
Integrations
- How to build an MCP server for ECI JobBOSS2How to build a Model Context Protocol server for ECI JobBOSS2: read-only tools, SQL Server auth, stdio vs HTTP transports, permission scoping and audit logging.
- How to use Claude with ECI E2 Shop SystemHow to use Claude with ECI E2 Shop System: MCP connectors, Anthropic API, AWS Bedrock or Vertex options, data handling, and the on-prem alternative.
Software
- ECI JobBOSS2Independent profile of ECI JobBOSS2, a job shop ERP: what it does, main modules, integration options, strengths, limits, alternatives and where AI can help.
- ECI E2 Shop SystemIndependent profile of ECI E2 Shop System, a job shop ERP: what it does, core modules, integration options, strengths, limits, alternatives and AI use cases.