apec-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@apec-mcpupdate my job-search preferences"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
APEC MCP Server
MCP (Model Context Protocol) server that exposes the APEC candidate-profile API as tools for any MCP-compatible AI assistant.
API Analysis
API Type
Proprietary REST / JSON over HTTPS.
Not publicly documented. Discovered via browser network capture (HAR files).
Base URL: https://www.apec.fr/cms/webservices/
Authentication
Cookie-based session auth — no OAuth, no API key.
Required cookies (obtained by logging in on apec.fr):
Cookie | Purpose | Lifetime |
| Server-side session (Java/Spring backend) | Session |
| Bot-detection token | Hours |
| User identity (XML payload) | Long |
| Activity tracking | Long |
| Load-balancer affinity | Session |
Action required: When the server starts returning 401/403, copy fresh cookies from DevTools → Network → any
/cms/webservices/*request → Cookie header, and update.env.
Reflection / Introspection
There is no public API schema (no OpenAPI spec, no GraphQL introspection).
The API was reverse-engineered from three browser sessions:
www.apec.fr.har— initial profile creationwww2.apec.fr.har— portfolio/strengths editingwww3.apec.fr.har— full profile editing (business card, photo upload, reference data)
The backend appears to be a Java Spring application (JSESSIONID, Jahia CMS static assets).
Related MCP server: resume-mcp
API Endpoints
Profile
Method | Path | Description |
GET |
| Full profile (the canonical object) |
POST |
| Save experiences + education |
POST |
| Save job-search preferences |
POST |
| Save skills + strengths |
POST |
| Save personal / contact info |
POST |
| Validate before saving |
GET |
| UI display flag |
GET |
| Photo upload paths |
Stats
Method | Path | Description |
GET |
| Total profile views |
GET |
| Days since publication |
GET |
| Views trend (float) |
POST |
| Unread recruiter messages |
POST |
| Saved contacts count |
Search / Autocomplete
Method | Path | Description |
GET |
| Job-title search |
GET |
| General search |
Reference Data
Method | Path | Description |
POST |
| Enum lists (869 entries) |
GET |
| Métier taxonomy node |
GET |
| Country list |
Identification & CV
Method | Path | Description |
GET |
| Current user info |
GET |
| Uploaded CV files |
GET |
| Job-recommendation subscription |
Data Model (TypeSpec)
import "@typespec/rest";
import "@typespec/http";
using TypeSpec.Rest;
using TypeSpec.Http;
// ── Shared ──────────────────────────────────────────────────────────────
model Audit {
dateCreation: int64; // epoch ms
dateModification: int64 | null;
utilisateurCreation: string;
utilisateurModification: string | null;
}
// ── Reference / enum entries ─────────────────────────────────────────────
model ReferenceItem {
codePresentation: string;
idNomenclature: int64;
codeNomenclature: string;
idOrganisation: int64;
idOrganisationParent: int64 | null;
libelle: string;
niveau: int32;
ordre: int32;
}
// ── Sub-models ───────────────────────────────────────────────────────────
model Experience {
intitulePoste: string;
idNomFonction: int64;
idNomMetier: int64;
dateEntree: string; // ISO 8601
dateSortie: string | null;
nomEntreprise: string;
expNonCadre: boolean;
numeroOrdre: int32;
audit: Audit;
}
model Formation {
intituleFormation: string;
dateEntree: string; // ISO 8601
dateSortie: string | null;
idNomDiscipline: string;
idNomNiveau: string;
organismeFormation: string | null;
numeroOrdre: int32;
audit: Audit;
}
enum CompetenceType {
LANGUE,
SAVOIR_ETRE,
TECHNIQUE,
METIER,
}
model Competence {
libelle: string;
type: CompetenceType;
idNomCompetence: int64;
idNomNiveau: int64 | null;
miseEnAvant: boolean;
idProfilCadre: int64;
audit: Audit;
id: int64;
}
model AdressePostale {
adresseNumeroEtVoie: string;
adresseCodePostal: string;
adresseVille: string;
adresseBatimentImmResidence: string | null;
adresseComplementAdresse: string | null;
idPays: int64;
audit: Audit;
id: int64;
}
model SouhaitSecteur { idNomSecteurActivite: int64; audit: Audit; id: int64; }
model SouhaitFonction { idNomFonction: int64; idNomMetier: int64; audit: Audit; id: int64; }
model SouhaitContrat { idNomTypeContrat: int64; audit: Audit; id: int64; }
model SouhaitEntreprise{ idNomTailleEntreprise: int64; audit: Audit; id: int64; }
model SouhaitTemps { idNomTempsTravail: int64; audit: Audit; id: int64; }
model SouhaitMode { idNomModeTravail: int64; audit: Audit; id: int64; }
model SouhaitLieu { idNomLieu: int64; distance: int32 | null; audit: Audit; id: int64; }
// ── Full profile ─────────────────────────────────────────────────────────
model ProfilCadre {
id: int64;
idProfilCadre: int64;
idCompteCadre: int64;
idNomStatut: int64;
idNomStatutCandidat: int64;
// Personal info
idNomCivilite: int64;
nom: string;
prenom: string;
dateNaissance: int64; // epoch ms
adressePostale: AdressePostale;
adresseEmail: string;
numeroTelephoneMobile: string;
lienLinkedin: string | null;
photo: string | null;
// Professional summary
metierSouhaite: string;
objectifProfessionnel: string | null;
pointsClesProfessionnels: string | null;
idNomAnneesExperience: int64;
idNomDelaiDisponibilite: int64;
remunerationMinimale: float32;
indicateurMasquerSalaire: boolean;
pretPourRecrutement: boolean;
// Preferences
souhaitsSecteurs: SouhaitSecteur[];
souhaitsFonctions: SouhaitFonction[];
souhaitsContrats: SouhaitContrat[];
souhaitsEnts: SouhaitEntreprise[];
souhaitsTemps: SouhaitTemps[];
souhaitsModes: SouhaitMode[];
souhaitsLieux: SouhaitLieu[];
// Experiences & formations
experiencesCles: Experience[];
formationsCles: Formation[];
// Skills
competences: Competence[];
atouts: string[];
portfolios: unknown[];
// CV
idCvFichier: int64 | null;
// Completion indicators
tauxRemplissage: int32;
indicateurCompletCompetence: boolean;
indicateurCompletCompMea: boolean;
indicateurCompletPortfolio: boolean;
// Versioning
numeroVersion: int32;
numeroVersionCadre: int32;
audit: Audit;
auditCadre: Audit;
}
// ── User identity ────────────────────────────────────────────────────────
model ApecUser {
id: string;
numeroCompte: string;
nom: string;
prenom: string;
email: string;
cadre: boolean;
actif: boolean;
token: string;
sessionId: string;
}MCP Tools
Tool | APEC endpoint | Description |
| GET | Authenticated user details |
| GET | Full profile (use as base for updates) |
| GET | Views, duration, trend |
| GET | Uploaded CVs |
| POST | Unread recruiter messages |
| POST | Validate before saving |
| POST | Experiences + education |
| POST | Job-search preferences |
| POST | Skills + strengths |
| POST | Personal / contact info |
| GET | Job-title autocomplete |
| GET | General search |
| GET | Métier taxonomy |
| POST | Enum reference data |
Update pattern
All update endpoints require the complete profile object (not a partial patch).
profile = get_profile()
profile["experiencesCles"].append({...})
update_experiences_formations(profile)Key Use Case — Fill Profile from LinkedIn or CV
The intended end-to-end workflow:
1. [LinkedIn MCP] get_my_profile() → raw LinkedIn data
OR parse CV text (PDF / plain text)
2. [APEC MCP] get_reference_lists([…]) → resolve enum IDs
search_metiers(q=…) → find idNomMetier / idNomFonction
3. AI assistant maps fields:
LinkedIn title → metierSouhaite + experiencesCles[].intitulePoste
LinkedIn positions → experiencesCles[]
LinkedIn education → formationsCles[]
LinkedIn skills → competences[]
LinkedIn location → adressePostale + souhaitsLieux[]
4. [APEC MCP] get_profile() → fetch current profile
update_experiences_formations(…) → save
update_informations_complementaires(…)
update_atouts(…)
update_carte_de_visite(…)Setup & Run
Prerequisites
uv installed
Docker / Apple Container with Compose support
Local development
cp .env.example .env
# Edit .env — paste fresh cookies from DevTools
uv sync
uv run apec-mcp # SSE on http://localhost:8080/sse
# or
MCP_TRANSPORT=stdio uv run apec-mcpDocker (Apple Container / Socktainer)
# First run — build and generate lock file locally
uv lock
docker compose up --buildThe MCP server is available at http://localhost:8080/sse.
MCP client config
{
"mcpServers": {
"apec": {
"url": "http://localhost:8080/sse"
}
}
}Session Refresh
Cookies expire. When you see 401/403:
Open
https://www.apec.fr→ log inDevTools → Network → any
/cms/webservices/*request → Headers → CookieCopy the full
Cookie:value into.envasAPEC_COOKIES=...docker compose restart
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/clement-igonet/apec-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server