AI quoting agent for electronics distributors. RFQ in, quote out via MCP tools.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Your sales engineers are spending 2-4 hours turning RFQ documents into quotes. This does it in seconds.
Electronics RFQ Agent is a Python library and CLI that reads RFQ documents (PDF, Excel, Word), looks up every line item against your ERP catalog, and outputs a draft quote. It connects to SAP, Epicor, Oracle, and Microsoft Dynamics through MCP servers, so it works with Claude, GPT-4, or any agent framework that speaks MCP.

To install from source instead:
Parsing RFQ documents (PDF, Excel, Word) calls the Anthropic API, so set ANTHROPIC_API_KEY before running anything that touches a real document:
You don't need this key to run erfa audit against an existing quote file, or to explore the CLI with --help. Only document parsing calls out to Claude.
We were working with electronics distributors who had 3-5 sales engineers spending most of their day on quote entry. Every tool we found was either tied to one specific ERP or required a 6-month integration project. We wanted something that worked with what distributors already had, could be self-hosted (quote data is sensitive), and was actually extensible.
The MCP architecture means adding a new ERP is writing one file. The parser handles the document formats distributors actually send: hand-filled PDFs, multi-sheet Excel files, and the occasional scanned table.
No ERP system required to try it out; the mock backend ships with 200 realistic electronics parts. You do need ANTHROPIC_API_KEY set, since parsing the RFQ document is still a real Claude call:
MockERP applies quantity-based pricing tiers automatically: qty >= 1000 gets 20% off, qty >= 100 gets 10% off, qty >= 10 gets 5% off. List price applies below qty 10. This mirrors real-world volume pricing so benchmarks and integration tests reflect realistic cost curves.
Connect to a real ERP:
erfa ships two subcommands. Every flag below is pulled straight from erfa --help.
| Command | Arguments | Flags | What it does |
|---|---|---|---|
erfa quote | rfq (path, required) | --mock, --margin <float> (default 0.15), --output/-o <path> | Parses an RFQ file and prints a draft quote. Needs ANTHROPIC_API_KEY; parsing always goes through Claude, --mock only swaps the ERP backend. |
erfa audit | quote_file (path, required) | none | Prints a full audit report (found / substituted / not found, fill rate) for a quote JSON file saved with erfa quote --output. Reads a local file only, no API key needed. |
erfa mcp | none | none | Launches an MCP stdio server exposing quote_rfq, lookup_part, and audit_quote as typed tools, so any MCP-compatible agent (Claude, GPT-4, Gemini) can call them directly without shelling out to the CLI. Point your MCP client config at erfa mcp as the command. |
Audit output example (real output from erfa audit docs/example-quote.json, generated by running the mock ERP's pricing logic against the sample RFQ in tests/fixtures/sample_rfq.txt):
Zero-price parts: If a part exists in the ERP catalog but has a unit price of $0.00, the agent quotes $0 rather than skipping the line, and sets
line.notesto a message flagging the zero price so you catch it before quoting the customer. Checkline.notesfor any found or substituted line before sending a quote out.
The full reference lives in docs/api.md: every QuoteAgent parameter, the shared ERP connector interface, Quote/QuoteLineItem field-by-field, and the exception hierarchy. The exports below are what from electronics_rfq_agent import ... actually gives you, grepped from src/electronics_rfq_agent/__init__.py, not guessed:
| Export | What it is |
|---|---|
QuoteAgent | Orchestrates parsing + ERP lookup + quote assembly. run() (async) and run_sync(). |
EpicorMCP, SAPMCP, OracleMCP, DynamicsMCP | ERP connectors, one per supported system. All implement the same search_parts / get_part / get_price / check_inventory interface. |
MockERP (from electronics_rfq_agent.mcp.mock) | In-memory backend with 200 realistic parts. No credentials, no network. |
Quote, QuoteLineItem, RFQLineItem, ERPPartResult, ERPConfig | Pydantic v2 models for the quote, each line, the parsed RFQ line, raw ERP data, and connector config. |
ERPConnectionError, RFQParseError | The two exceptions QuoteAgent can raise: connection/auth failures and unparseable documents. Per-line ERP failures don't raise; they land in line.notes instead. |
TelemetryCollector, TelemetryEvent | Opt-in local telemetry (telemetry=True on QuoteAgent), counts and timings only, no RFQ content. |
| Electronics RFQ Agent | Manual process | SAP Joule | Generic AI (ChatGPT) | |
|---|---|---|---|---|
| Multi-ERP support | SAP + Epicor + Oracle + Dynamics | N/A | SAP-centric (Joule Studio can reach non-SAP sources via SAP Integration Suite) | No ERP access |
| Quote time (50 lines) | ~15s | 2-4 hours | Not publicly documented | N/A |
| Self-hostable | Yes | N/A | No (SAP BTP cloud service) | No |
| Data stays local | Yes | Yes | No | No |
| Open source | MIT | N/A | No | No |
| Dev mock backend | Yes | N/A | Not publicly documented | N/A |
| MCP compatible | Yes | N/A | Not publicly documented | No |
| ERP | Status | Connection | Docs |
|---|---|---|---|
| Epicor Kinetic | Supported | REST API | Setup |
| SAP ECC / S/4HANA | Beta (manual install) | PyRFC (BAPI) | Setup |
| Oracle Cloud SCM | Supported | REST API | Setup |
| Microsoft Dynamics 365 | Supported | Graph API | Setup |
| Mock backend | Built-in | In-memory | No config needed |
SAP note: pyrfc requires the SAP NetWeaver RFC Library, which is not on PyPI and must be downloaded manually from SAP's support portal (S-user required). See docs/erp-setup/sap.md for step-by-step instructions.
Measured using the in-memory mock backend (200 realistic parts, no ERP system required). Run it yourself:
ERP lookup latency (100 individual lookups, mock backend):
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/electronics-rfq-agent)<a href="https://allmcps.com/mcp/electronics-rfq-agent"><img src="https://allmcps.com/api/badge/electronics-rfq-agent?style=directory" alt="Electronics Rfq Agent on AllMCPs" /></a>