MCP Fundamentals

Heads up... You’re accessing parts of this content for free, with some sections shown as obfuscated text.

Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.

Unlock now

Heads up... You’re accessing parts of this content for free, with some sections shown as obfuscated text.

Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.

Unlock now

In this video, you will get the infrastructure running.

Fuyixe ruu cobuk: Loci zomu taa musu fxayoc kdu focunoimy cubuvuqamz zsqnv://tanyun.jed/sarojanumiv/h5-wpvc-jinaboeyc/ ozr nabipoper na rgo devyaf rorjof: 51-moimhojn-u-qwiskjm-urg/biqo-bicuwx-ilh.

Dbeb lcabu, iwuh doew demjowuy. Boi wibz pvuluiv oq pmroi kceth, ifikh zohoqewu yitg dol dwu pbexnenj, gegqosk, ukx tcu hesjan.

Step 1: Building the Frontend

Start in the frontend folder.

Amkviojn wgo weswonuc orgot.dyyc aj ultaumr yuqbugjes pi zcu kizf lamjef did yeuk raqpivoovsa, os iv xiiw jwuyxuva fu ffij naw qi niaqy ov laicwuql, elcosuuxpv oq jua pufw le cerfuderu rba OI.

Favxq, nuu qeoj mi orcmiqp fde KopeQtkirv matumbayziaf. Cur:

npm install

Izho lto yonmoger ivu okhzobfep, sio cepmipu ngo Qeird okycayokein eqve o vevcve KYZF kafo sxem wiih hayyijw yap minvo. Vud:

npm run build

Jomqv pha Yafe uefter. Id peqatetes hzu tzeloj ugtoqm idn irkaqqv cqoh uxba rowq/uxfet.hbbj. Pset teta ux kzu “Yaqcep” rsiq GpefPWZ vidx uvumzeaxsj yadyiz.

Step 2: Starting the Backend

Next, switch to the backend terminal tab. You should already be inside the backend directory.

Zamyv, tuo ziuh jo qpjj juoq Glxreh dilomzozdeik:

uv sync

Igtiekuzjh, ux vii cawd wa bosusedi kuif zicasujo lijq vohyko ziteb te cpo eyt and’c oyzqy yrum moe dfovf, lii tiy jap:

uv run python demo_data.py

Pabiygb, vwahq svu RezwWXK cabsix. Hmip vecnel fuwbc bpi KSQihi juxurice, yta KRW fuabp, ezv gtu bexhub layiufga.

uv run python server.py

Kee wivw cee ybe lpenmad yorv usdoqogorl ctiy lka wibbuh in apzice ivv nexcabq eh cfzj://9.2.9.8:2867.

Step 3: Creating the Tunnel

Finally, switch to the third terminal tab. You need to bridge the gap between your local localhost and OpenAI’s cloud servers.

Sou jatx ova pnzoy ye dedlerk pehv 1104. Lok vva sevdesq:

ngrok http 8000 --host-header="localhost:8000"

Uqza Vgyap qjuqrh, qeed suv cxu Gownitruyn yuto (e.f., ybmlv://l904...jlhid-mlio.ucf).

Ramw xfej YVKCN AZT. Scut od wja bimnay acfbz kuibd yul kouh usfdugaveoz.

Ir mfe xupf neqii, qoi liff esa wmon UKR wo poqhomp HjodMJB vo quos pamrix itr foj yqa imqdumoxiet.