Content Tools

backlight.ai

Provides search and retrieval of Backlight.ai site content, case studies, and FAQ entries through multiple search methods.

1 endpoint12 known toolsFirst detected August 15, 2026Last detected August 15, 2026

ENDPOINT 1

https://mcp.backlight.ai/mcp

No auth detected

MCP server metadata

Name: Backlight.ai
Version: 3.4.5

Capabilities

experimentalloggingprompts.listChangedresources.listChangedtools.listChangedextensions.io.modelcontextprotocol/ui

Server instructions

Backlight.ai MCP server (v2). Het corpus bestaat uit: (1) klantprojecten/cases, (2) site-inhoud (diensten, methodologie, prijzen), (3) veelgestelde vragen, en (4) een proposalformulier. Gebruik de juiste tool per vraagtype: search_cases voor portfoliovragen en klantreferenties; get_case voor de volledige inhoud van een specifieke case op basis van slug; cases://index (resource) voor een snelle lijst van alle gepubliceerde case-slugs; search_docs voor algemene vragen over diensten, tarieven, aanpak of methodologie; search_faq voor korte, directe vragen over hoe Backlight werkt; semantic_search voor embeddings-gebaseerde (RAG) retrieval over docs en cases; de BM25-tools blijven de standaard voor dit gecureerde corpus; query_case_graph om relaties tussen cases te doorlopen (gedeelde klanten, domeinen, technologieen) bij 'gerelateerd aan'- of 'vergelijkbare cases'-vragen; list_terms om vocabulaire te verduidelijken voordat je search_docs aanroept; request_proposal uitsluitend als de gebruiker expliciet een offerte of intake wil starten (vereist: domain, contact_email, brief). Proposal-flow: verzamel eerst context via search_cases + search_docs, vat samen voor de gebruiker, en roep dan pas request_proposal aan. Geen em-dash gebruiken in output.

Known tools 12

search_docs

Returns ranked Backlight.ai site-content sections (search_result blocks with citations) from all site pages: services, pricing, methodology, and legal pages (terms & conditions, privacy policy, cookie policy, security policy, accessibility statement).

Inferred read-only

search_cases

Returns ranked Backlight.ai portfolio cases as CaseSummary objects (slug, title, client, year, sector, summary) using BM25 + Dutch stemming.

Inferred read-only

semantic_search

Returns ranked Backlight.ai site-content sections (search_result blocks with citations) using embedding-based (vector) retrieval over the case + docs corpus AND the FAQ (matching FAQ entries are cited as /docs/faq#<slug> deep links, mixed into the ranking).

Inferred read-only

get_case

Returns full CaseDetail for one Backlight.ai case (frontmatter metadata + complete markdown body) by slug.

Inferred read-only

search_faq

Returns matching Backlight.ai FAQ entries as FaqItem objects (category, question, answer, homepage, url) ranked by BM25 + Dutch stemming.

Inferred read-only

search_faq_vectors

Search THIS organisation's FAQ by meaning (semantic vector search).

Inferred read-only

search_pois

Search the current organisation's Points of Interest (POIs) by category.

Inferred read-only

submit_feedback

Store visitor feedback about the current conversation.

Inferred read-only

set_map_pin

Pinpoint a location for the visitor on the map.

Inferred read-only

list_terms

Returns up to 150 Term objects (term + frequency count) derived from the Backlight.ai site corpus.

Inferred read-only

request_proposal

Writes a proposal-intake record to the Backlight.ai CRM and returns a ProposalTicket (ticket_id).

Inferred read-only

query_case_graph

Filters Backlight.ai portfolio cases by typed graph criteria (technique, sector, orgtype, tier, quality, certification, client, event, tag, partner).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.backlight-ai]
url = "https://mcp.backlight.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "backlight-ai": {
      "type": "http",
      "url": "https://mcp.backlight.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: backlight-ai
Remote MCP URL: https://mcp.backlight.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "backlight-ai": {
      "url": "https://mcp.backlight.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "backlight-ai": {
      "type": "http",
      "url": "https://mcp.backlight.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "backlight-ai",
  "transport": "streamable-http",
  "url": "https://mcp.backlight.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for backlight.ai was fetched 2026-08-23T21:46:53.851Z.

Trust status Trusted

backlight.ai is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.