Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Actual group – offres d'emploi

REMOTE · WWW.ACTUALGROUP.COM

Search Actual group job offers in France, find agencies and prepare applications.

+2 this week 73 Trust /100

Last scanned (9 hours ago)

Scores higher than 60% of remote servers

Reachable. Last reached 5 Nov 2026.

Category CRM and Sales

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability100
Schema Quality & AI Usability59
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2340 tokens (~390/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management14
  • Stability check failed: schema churn in the 20 days we've observed: 0 tool removals, 5 breaking changes, 0 auth/transport breaks, 1 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 5 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 11 to 14.

  • 3 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 4 to 7.

  • 24 Oct 26 +1
    • Schema quality: 486 → 390 ▲ functional
    • “find_agencies” reworded the description of “context” cosmetic
    • “find_best_agency” reworded the description of “context” cosmetic
    • “get_offer” reworded the description of “context” cosmetic
    • “list_offer_facets” reworded the description of “context” cosmetic
    • “search_offers” reworded the description of “context” cosmetic
    • “start_application” reworded the description of “context” cosmetic
  • 23 Oct 26 −5
    • Stability: 0.20 → fail ▼ security
    • A breaking change shipped without a version bump: still 1.0.0 ▼ security
    • Tool “find_agencies” rewrote its description, which is the text the model reads security
    • Schema quality: 165 → 486 ▼ functional
    • “find_agencies” added a required parameter “context”, so existing callers break ▼ functional
    • “find_agencies” added a required parameter “llm_model”, so existing callers break ▼ functional
    • “get_offer” added a required parameter “context”, so existing callers break ▼ functional
    • “get_offer” added a required parameter “llm_model”, so existing callers break ▼ functional
    • “list_offer_facets” added a required parameter “context”, so existing callers break ▼ functional
    • “list_offer_facets” added a required parameter “llm_model”, so existing callers break ▼ functional
    • “search_offers” added a required parameter “context”, so existing callers break ▼ functional
    • “search_offers” added a required parameter “llm_model”, so existing callers break ▼ functional
    • “start_application” added a required parameter “context”, so existing callers break ▼ functional
    • “start_application” added a required parameter “llm_model”, so existing callers break ▼ functional
    • Schema quality: good → excellent functional
    • New tool “find_best_agency” functional
    • “find_agencies” added an optional parameter “conversation_id” cosmetic
    • “get_offer” added an optional parameter “conversation_id” cosmetic
    • “list_offer_facets” added an optional parameter “conversation_id” cosmetic
    • “search_offers” added an optional parameter “agencyCode” cosmetic
    • “search_offers” added an optional parameter “conversation_id” cosmetic
    • “start_application” added an optional parameter “conversation_id” cosmetic
  • 21 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Oct 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 16 Oct 26 72

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://www.actualgroup.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=actualgroup.com CN=WR3,O=Google Trust Services,C=US 6 Oct 2026 4 Jan 2027 RSA 2048 SHA256-RSA 5edf89869c43fd2910da8c3738f862ec
SANs: actualgroup.com, www.actualgroup.com
CN=WR3,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7ff005a91568d63abc22861684aa4b5a
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of www.actualgroup.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
actualgroup.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=604800

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://www.actualgroup.com/mcp Verified 200
http (plaintext) http://www.actualgroup.com/mcp HTTPS enforced 301 https://www.actualgroup.com:443/mcp
MCP tools · 6 exposed · ~2,283 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
find_agencies ~313

Actual group employment agencies (about 780 in France) in a town or a region, with address and specialties. Candidates can visit or call an agency for advice, registration or follow-up on their applications. To recommend the single most relevant agency for a job, use find_best_agency instead.

NameTypeReqDescription
citystring–Town name, e.g. "Nantes".
contextstringyesWhy are you calling this tool? Describe the job seeker's or recruiter's goal in one short sentence. Do not include names, emails or phone numbers.
conversation_idstring–Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee…
limitinteger–Maximum number of agencies returned. Defaults to 20.
llm_modelstringyesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model…
regionstring–French region name, e.g. "Pays de la Loire".

No output schema declared.

No examples provided.

find_best_agency ~505

Recommend the Actual group agency, office, training centre or school best suited to a person's need, near a place in France. Covers employment agencies (intérim, CDD, CDI), Actual Talent offices (talent acquisition and assessment, mostly white-collar), Envergure centres (vocational training, skills assessment, career transition) and the group's schools (eSUP, Holberton…, often work-study). Ranks them by open offers for the given job, specialty (construction, logistics, medical, white-collar, school domain…) and distance. Returns address, phone, opening status and why each agency was picked. Pass the returned agency code to search_offers (agencyCode) to list that agency's offers.

NameTypeReqDescription
contextstringyesWhy are you calling this tool? Describe the job seeker's or recruiter's goal in one short sentence. Do not include names, emails or phone numbers.
conversation_idstring–Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee…
jobstring–Job or field the person is looking for or hiring for, e.g. "électricien", "cariste", "aide-soignant".
limitinteger–Number of agencies to return, 1 to 5. Defaults to 3.
llm_modelstringyesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model…
locationstringyesFrench town or postal code, e.g. "Le Mans" or "72000".
purposestring–find_job: a candidate looking for work (default). hire: a company looking to recruit. assessment: a company wanting candidates or staff assessed (Actual Talent). training: vocational training, skills…

No output schema declared.

No examples provided.

get_offer ~276

Full details of one Actual group job offer: description, required profile, salary, schedule, benefits and recruiting agency. Takes the slug returned by search_offers (also the last segment of the offer URL).

NameTypeReqDescription
contextstringyesWhy are you calling this tool? Describe the job seeker's or recruiter's goal in one short sentence. Do not include names, emails or phone numbers.
conversation_idstring–Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee…
langstring–Language of the offer text. Defaults to fr.
llm_modelstringyesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model…
slugstringyesOffer slug, from search_offers or the offer URL.

No output schema declared.

No examples provided.

list_offer_facets ~285

Exact filter values accepted by search_offers for one dimension (contract type, job family, industry or region), with the number of open offers for each. Optionally scoped by a query and a town.

NameTypeReqDescription
contextstringyesWhy are you calling this tool? Describe the job seeker's or recruiter's goal in one short sentence. Do not include names, emails or phone numbers.
conversation_idstring–Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee…
dimensionstringyesWhich filter to list.
llm_modelstringyesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model…
qstring–Optional free text to scope the counts.
townstring–Optional town or postal code to scope the counts.

No output schema declared.

No examples provided.

search_offers ~534

Search the job offers (temporary work, fixed-term and permanent contracts) published by Actual group in France. Combine a free-text query with a town and filters. Filter values for contractType, family, industry and region must be exact French values: get them from list_offer_facets. Use get_offer with a result's slug for the full offer.

NameTypeReqDescription
agencyCodestring–Only offers handled by this agency: the agency code returned by find_best_agency.
contextstringyesWhy are you calling this tool? Describe the job seeker's or recruiter's goal in one short sentence. Do not include names, emails or phone numbers.
contractTypearray–Contract types (exact values from list_offer_facets), e.g. ["Contrat de travail temporaire", "CDI"].
conversation_idstring–Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee…
familyarray–Job families (exact values from list_offer_facets).
industryarray–Industries (exact values from list_offer_facets).
langstring–Language of the offer texts and URLs. Defaults to fr.
llm_modelstringyesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model…
pageinteger–Page number, from 1.
pageSizeinteger–Results per page, 1 to 20. Defaults to 10.
qstring–Free text: job title, skill or keyword, e.g. "cariste", "soudeur TIG", "aide-soignant".
radius––Search radius in km around the town. Defaults to 20.
regionarray–French regions (exact values from list_offer_facets), e.g. ["Bretagne"].
sortstring–Sort order. Defaults to relevance.
townstring–French town or postal code to search around, e.g. "Rennes" or "35000".

No output schema declared.

No examples provided.

start_application ~370

Prepare an application to an Actual group offer on behalf of the candidate you are assisting. Returns a personal link, valid 72 hours, that the candidate must open to attach their CV and give consent to the processing of their data; the application is only sent once they submit that page. Only call this when the candidate has asked to apply and given you their name and email. Never submit the page yourself: give the link to the candidate.

NameTypeReqDescription
contextstringyesWhy are you calling this tool? Describe the job seeker's or recruiter's goal in one short sentence. Do not include names, emails or phone numbers.
conversation_idstring–Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Kee…
emailstringyesCandidate email address.
firstNamestringyesCandidate first name.
langstring–Language of the application page. Defaults to fr.
lastNamestringyesCandidate last name.
llm_modelstringyesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model…
phoneNumberstring–Candidate phone number, optional.
slugstringyesSlug of the offer, from search_offers or get_offer.

No output schema declared.

No examples provided.

Install

How do I install the Actual group – offres d'emploi MCP server?

Actual group – offres d'emploi is a hosted endpoint at https://www.actualgroup.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · www.actualgroup.com

# add to Claude Code
claude mcp add --transport http com-actualgroup-jobs 'https://www.actualgroup.com/mcp'
Common questions

What is the Actual group – offres d'emploi MCP server?

Actual group – offres d'emploi is an MCP server listed in the public MCP registry as com.actualgroup/jobs. Search Actual group job offers in France, find agencies and prepare applications. This page covers its hosted endpoint (https://www.actualgroup.com/mcp).

Is the Actual group – offres d'emploi MCP server safe to use?

Actual group – offres d'emploi scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Actual group – offres d'emploi MCP server expose?

Actual group – offres d'emploi exposes 6 tools: find_agencies, find_best_agency, get_offer, list_offer_facets, search_offers, start_application. Their descriptions and schemas cost roughly 2,283 tokens of context every time the server is loaded.

Does the Actual group – offres d'emploi MCP server require authentication?

No. We connected to Actual group – offres d'emploi without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Actual group – offres d'emploi MCP server still maintained?

Actual group – offres d'emploi is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.