MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Other

ir.cbest/lighting

Iranian lighting supplier directory: products, brands, and a bilingual Persian/English taxonomy.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
1837 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
8

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
310
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 1837 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-06-18, serverInfo.name cbest-lighting.

  • Pass
    Lists tools

    tools/list returned 8 tools.

  • Pass
    Current protocol

    Negotiated 2025-06-18. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 1837 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 1837 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    16 of 16 parameters have a description (100%). The bar is 80%.

  • Fail
    Safety hints

    8 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-09-21T18:56:37.123447Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using ir.cbest/lighting

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http ir-cbest-lighting https://www.cbest.ir/lighting/api/mcp

Capabilities

Tools 8

classify_lighting_term

Map any Persian or English lighting phrase onto the canonical taxonomy — «داون‌لایت توکار», 'trimless plaster frame', 'high bay'. Backed by 522 learned type→category pairs plus rules measured at 95% agreement. Returns null for a phrase that names no category rather than guessing.

Discovered
compare_brands

Which suppliers cover a category, with counts, share, and per-facet data coverage. Coverage describes what each supplier's SOURCE stated, never product quality, and a one-supplier category says so rather than pretending to be a comparison.

Discovered
get_brand

One supplier in full: what they make, the product families they run, and — the field worth the call — doesNotDo, a statement of what they genuinely do NOT make, computed from absence in their product list rather than inferred from their marketing.

Discovered
get_product

Every field on file for one product, by the id search_products returns ('brand/product-slug'), including provenance: whether the fact came from the supplier's own website or from a page of their PDF catalog, and when it was read.

Discovered
list_brands

Every supplier on file with what they cover, how complete their data is, and when it was last read. No contact details — see the server instructions.

Discovered
list_categories

The 20 canonical categories with Persian and English names, product counts, and which suppliers are in each. Small enough to fetch once and reason over the whole market; flags categories that only one supplier covers.

Discovered
search_products

Search the catalog of real products stocked by the suppliers on file. Accepts Persian or English. Returns normalized facets (mounting, indoor/outdoor, IP, colour temperature, and wattage/lumen where stated) plus what the query matched on. Colour temperature is returned but is NOT filterable: a fixture is usually sold in several, and the row carries the one its source printed. The response always reports what the filters excluded and why, split into 'not stated in our data' and 'did not match' — a product missing from a result is NEVER evidence that a supplier does not make it; use get_brand's doesNotDo for that.

Discovered
start_consultation

Turn a described need into a link the person opens themselves, where an adviser builds a brief and matches it against suppliers' real stock. This is how someone actually reaches a supplier: there are no contact details in this server, and this call does not contact anyone. It stores nothing and it REFUSES any personal data — no name, no number, no email. Describe the project, not the person.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected1837 ms8