# Taminyaran Engineering MCP (remote · mcp.taminyaran.com)

Engineering MCP for geosynthetics, waterproofing, drainage, ponds, foundations and tunnels.

- Trust score: 64/100 (medium)
- Change this week: +10
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

> **Recent critical change**: Authorization (2026-10-30). See the changelog below before you install this server.

## Components

- remote · `mcp.taminyaran.com`: 64/100 (this document), [markdown](https://verifymcp.io/servers/saeedfaai-taminyaran-engineering/mcp.md), [page](https://verifymcp.io/servers/saeedfaai-taminyaran-engineering/mcp)

## Channel facts

- Endpoint: `https://mcp.taminyaran.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.5.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (submit_quote_request).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 53/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 2914 tokens (~69/item across 42 items; 42 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 42 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 43 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Taminyaran Engineering MCP server?

Taminyaran Engineering MCP is a hosted endpoint at https://mcp.taminyaran.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.

### Claude

```bash
claude mcp add --transport http saeedfaai-taminyaran-engineering 'https://mcp.taminyaran.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "saeedfaai-taminyaran-engineering": {
      "url": "https://mcp.taminyaran.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "saeedfaai-taminyaran-engineering": {
      "type": "http",
      "url": "https://mcp.taminyaran.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.saeedfaai-taminyaran-engineering]
url = "https://mcp.taminyaran.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "saeedfaai-taminyaran-engineering": {
      "type": "remote",
      "url": "https://mcp.taminyaran.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add saeedfaai-taminyaran-engineering --url 'https://mcp.taminyaran.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  saeedfaai-taminyaran-engineering:
    url: "https://mcp.taminyaran.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "saeedfaai-taminyaran-engineering": {
      "Transport": "http",
      "Url": "https://mcp.taminyaran.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add saeedfaai-taminyaran-engineering -t streamable-http -u 'https://mcp.taminyaran.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "saeedfaai-taminyaran-engineering": {
      "type": "http",
      "url": "https://mcp.taminyaran.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] New tool “workspace_rotate_key”, which the server declares destructive
- [security] New tool “workspace_update_intake”, which the server declares destructive
- [functional regression] Schema quality: 2204 → 2914
- [functional] Server version: 0.7.0 → 0.11.0
- [functional] New tool “workspace_add_evidence”
- [functional] New tool “workspace_create_project”
- [functional] New tool “workspace_create_quote_handoff”
- [functional] New tool “workspace_describe”
- [functional] New tool “workspace_get_handoff”
- [functional] New tool “workspace_get_project”
- [functional] New tool “workspace_prepare_quote_handoff”
- [functional] New tool “workspace_review_readiness”
- [functional] New tool “workspace_run_intake”

### 2026-11-02 (score 63, +1)

- [functional improvement] Schema quality: 112 → 71
- [functional] Server version: 0.5.1 → 0.7.0
- [functional] New tool “abiyar_assess_suitability”
- [functional] New tool “abiyar_calendar_feed”
- [functional] New tool “abiyar_chill_profile”
- [functional] New tool “abiyar_context”
- [functional] New tool “abiyar_describe”
- [functional] New tool “abiyar_get_crop”
- [functional] New tool “abiyar_get_knowledge_cards”
- [functional] New tool “abiyar_get_provenance”
- [functional] New tool “abiyar_get_rootstocks”
- [functional] New tool “abiyar_get_sources”
- [functional] New tool “abiyar_get_taxonomy”
- [functional] New tool “abiyar_get_varieties”
- [functional] New tool “abiyar_location_fingerprint”
- [functional] New tool “abiyar_location_profile”
- [functional] New tool “abiyar_network_screen”
- [functional] New tool “abiyar_pond_design”
- [functional] New tool “abiyar_search_evidence”
- [functional] New tool “abiyar_soil_assess”
- [functional] New tool “abiyar_variety_fit”
- [functional] New tool “abiyar_water_need”
- [functional] New tool “get_calculator_spec”
- [functional] New tool “list_calculators”
- [functional] New tool “run_calculator”

### 2026-10-31 (score 62, +3)

- [security improvement] HSTS header: fail → pass

### 2026-10-30 (score 59, +5)

- [critical regression] Authorization: unverified → fail
- [security improvement] HTTPS: fail → pass

### 2026-10-29 (score 54, −6)

- [security regression] HTTPS: unverified → fail
- [security regression] Authorization: partial → unverified
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] New tool “submit_quote_request”, which the server declares destructive
- [functional regression] Schema quality: 94 → 112
- [functional] Server version: 0.5.0 → 0.5.1
- [functional] New tool “prepare_quote_request”

### 2026-10-28 (score 60, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “design_project” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 79 → 94
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.4.1 → 0.5.0
- [functional] New tool “project_intake”
- [cosmetic] “design_project” added an optional parameter “pump”

### 2026-10-27 (score 60)

First indexed and scored.

## MCP tools (42)

### `describe_capabilities` (~19 tokens)

Describe supported engineering domains, limits and data version.

### `search_materials` (~54 tokens)

Search curated Taminyaran local materials. Matches are candidates, not engineering approvals.

Input parameters:

- `family` (string)
- `limit` (integer)
- `project_type` (string)
- `query` (string)

### `get_material` (~24 tokens)

Get one curated material by asset_id.

Input parameters:

- `asset_id` (string, required)

### `design_project` (~197 tokens)

Versioned preliminary engineering design. Executable guarded modules include CAL-011 pond, CAL-060/061 foundation, CAL-063/064 tunnel, and CAL-065/066/067 excavation groundwater screens. High-risk engineering remains human-review.

Input parameters:

- `calculator_id` (string)
- `constraints` (object)
- `design_life_years` (number|null)
- `drainage` (object)
- `environment` (object)
- `fluid_or_medium` (string|null)
- `geometry` (object)
- `goal` (string)
- `groundwater` (object)
- `investigation` (object)
- `materials` (object)
- `project_type` (string, required)
- `pump` (object)
- `qa_qc` (object)
- `required_output` (string)
- `structure` (object)
- `tunnel` (object)
- `waterproofing` (object)

### `project_intake` (~157 tokens)

Normalize a project brief into a stateless machine-readable engineering intake. Excavation/foundation groundwater projects run CAL-065 network/perimeter, CAL-066 gravity HGL and CAL-067 pump TDH/wet-well screens. Missing values remain null and return HOLD; nothing is persisted.

Input parameters:

- `constraints` (object)
- `drainage` (object)
- `evidence` (object)
- `geometry` (object)
- `goal` (string|null)
- `groundwater` (object)
- `investigation` (object)
- `project_id` (string|null)
- `project_type` (string, required)
- `pump` (object)
- `required_output` (string|null)
- `structure` (object)

### `explain_design` (~27 tokens)

Explain a design_project payload supplied by the client. Stateless.

Input parameters:

- `design` (object, required)

### `prepare_quote_request` (~139 tokens)

Prepare a Taminyaran RFQ preview from an engineering design/BOQ. This tool NEVER submits. Show the returned summary to the user and obtain explicit confirmation before calling submit_quote_request.

Input parameters:

- `assumptions` (array)
- `boq` (array)
- `calculator_id` (string|null)
- `city` (string, required)
- `customer_name` (string, required)
- `design_id` (string|null)
- `notes` (string|null)
- `phone` (string, required)
- `product` (string, required)
- `project_type` (string|null)
- `quantity` (string, required)
- `warnings` (array)

### `submit_quote_request` (~163 tokens)

Submit a previously prepared RFQ to Taminyaran through the existing official quote form. CALL ONLY after the user explicitly confirms the exact prepare_quote_request summary. No arbitrary recipient is allowed. Do not retry automatically if submission status is unknown.

Input parameters:

- `assumptions` (array)
- `boq` (array)
- `calculator_id` (string|null)
- `city` (string, required)
- `confirmation_code` (string, required)
- `confirmed` (boolean, required)
- `customer_name` (string, required)
- `design_id` (string|null)
- `notes` (string|null)
- `phone` (string, required)
- `product` (string, required)
- `project_type` (string|null)
- `quantity` (string, required)
- `warnings` (array)

### `list_calculators` (~49 tokens)

List all 32 live canonical calculators from Taminyaran Calculation Center. Planned Master Map items are not falsely presented as executable.

Input parameters:

- `limit` (integer)
- `query` (string)

### `get_calculator_spec` (~36 tokens)

Get the live field contract, source and risk class for one Taminyaran site calculator.

Input parameters:

- `calculator_id` (string, required)

### `run_calculator` (~46 tokens)

Run one of the 32 live site calculators using the same canonical engine as Calculation Center Page 16700.

Input parameters:

- `calculator_id` (string, required)
- `inputs` (object, required)

### `abiyar_describe` (~25 tokens)

Describe live Abyar production architecture, stages, sources and MCP guardrails.

### `abiyar_get_taxonomy` (~39 tokens)

Read live Abyar crop taxonomy from Matrix. Optional query filters records.

Input parameters:

- `limit` (integer)
- `query` (string)

### `abiyar_get_crop` (~33 tokens)

Read one live Abyar crop/cultivar profile from Matrix and DB.

Input parameters:

- `crop_id` (string, required)

### `abiyar_location_profile` (~44 tokens)

Get Abyar modeled location/climate-zone profile for supplied coordinates. Stateless and not persisted by MCP.

Input parameters:

- `lat` (number, required)
- `lon` (number, required)

### `abiyar_water_need` (~102 tokens)

Run Abyar 12-month irrigation water-need logic. Missing inputs are returned instead of guessed.

Input parameters:

- `area_m2` (number, required)
- `climate_months` (array, required)
- `crop_id` (string)
- `efficiency` (number)
- `kc_monthly` (array)
- `kr` (number)
- `method` (string)
- `planting_date` (string)
- `stage_days` (object)

### `abiyar_network_screen` (~55 tokens)

Abyar preliminary irrigation network capacity screen.

Input parameters:

- `hours_available` (number, required)
- `irrigation_hours` (number, required)
- `peak_daily_m3` (number, required)
- `source_flow_m3h` (number, required)

### `abiyar_pond_design` (~74 tokens)

Run live Abyar rectangular pond geometry calculation.

Input parameters:

- `bottom_length_m` (number, required)
- `bottom_width_m` (number, required)
- `freeboard_m` (number, required)
- `top_length_m` (number, required)
- `top_width_m` (number, required)
- `total_depth_m` (number, required)

### `abiyar_context` (~48 tokens)

Build stateless Abyar context from crop and/or location and return next relevant calculations.

Input parameters:

- `crop_id` (string)
- `lat` (number)
- `lon` (number)

### `abiyar_search_evidence` (~56 tokens)

Search active Abyar evidence by subject and/or agronomic domain. Returns source-linked evidence rows without generating new claims.

Input parameters:

- `domain` (string)
- `limit` (integer)
- `subject_id` (string)

### `abiyar_get_sources` (~47 tokens)

List authoritative Abyar research/data sources, optionally filtered by country or institution type.

Input parameters:

- `country` (string)
- `limit` (integer)
- `type` (string)

### `abiyar_get_varieties` (~47 tokens)

List canonical active cultivars/varieties for a crop from the D1-backed Abyar research layer.

Input parameters:

- `crop_id` (string, required)
- `limit` (integer)

### `abiyar_get_rootstocks` (~46 tokens)

List canonical rootstocks for a crop with evidence, open conflicts, coverage and rootstock-context policy.

Input parameters:

- `crop_id` (string, required)
- `limit` (integer)

### `abiyar_location_fingerprint` (~79 tokens)

Build/read the rounded environmental fingerprint used by Abyar variety-fit policy from location plus optional soil/water context.

Input parameters:

- `lat` (number, required)
- `lon` (number, required)
- `province` (string)
- `soil_ece` (number)
- `soil_texture` (string)
- `water_ec` (number)

### `abiyar_variety_fit` (~81 tokens)

Run the canonical Abyar variety-fit policy for a crop and environmental fingerprint; optional cultivar/rootstock narrows context. MCP preserves upstream score and decision.

Input parameters:

- `crop_id` (string, required)
- `cultivar_id` (string)
- `fingerprint_key` (string, required)
- `limit` (integer)
- `rootstock_id` (string)

### `abiyar_chill_profile` (~72 tokens)

Read the canonical multi-model chill profile (Chill Hours, Utah Units, Dynamic Chill Portions) by fingerprint or coordinates. Full seasonal detail is optional.

Input parameters:

- `fingerprint_key` (string)
- `include_seasons` (boolean)
- `lat` (number)
- `lon` (number)

### `abiyar_soil_assess` (~45 tokens)

Run Abyar conservative soil/lab/water screening. It computes safe derived indicators but withholds fertilizer dose without calibrated local evidence.

Input parameters:

- `assessment` (object, required)

### `abiyar_get_knowledge_cards` (~67 tokens)

Read reviewed farmer/engineer knowledge cards for a crop with evidence/source references and cautions.

Input parameters:

- `audience` (string)
- `crop_id` (string, required)
- `limit` (integer)
- `status` (string)
- `topic` (string)

### `abiyar_get_provenance` (~31 tokens)

Trace provenance edges for a specific Abyar evidence ID.

Input parameters:

- `evidence_id` (string, required)

### `abiyar_calendar_feed` (~54 tokens)

Return location-aware Abyar crop calendar and weather alerts from the live calendar service. Forecast values are time-sensitive.

Input parameters:

- `crop_id` (string, required)
- `lat` (number, required)
- `lon` (number, required)

### `abiyar_assess_suitability` (~132 tokens)

Orchestrate Abyar environmental fingerprint + canonical variety-fit + reviewed cards + optional cultivar evidence and conservative soil assessment. It does not invent a new composite score.

Input parameters:

- `crop_id` (string, required)
- `cultivar_id` (string)
- `lat` (number, required)
- `limit` (integer)
- `lon` (number, required)
- `province` (string)
- `rootstock_id` (string)
- `soil_assessment` (object)
- `soil_ece` (number)
- `soil_texture` (string)
- `water_ec` (number)

### `workspace_describe` (~33 tokens)

Describe the separate Taminyaran Project Workspace state plane and bridge safety contract. Read-only; MCP itself remains stateless.

### `workspace_create_project` (~80 tokens)

Create a persistent PII-free Project Workspace and return project_id + one-time project_key. Use only after the user explicitly asks to persist project state. Never put project_key in a URL.

Input parameters:

- `confirm_persist` (boolean, required)
- `external_ref` (string|null)
- `intake` (object, required)
- `title` (string|null)

### `workspace_get_project` (~42 tokens)

Read persistent PII-free project state using explicit project_id + project_key capability handle.

Input parameters:

- `project_id` (string, required)
- `project_key` (string, required)

### `workspace_update_intake` (~62 tokens)

Replace the canonical PII-free project intake in Project Workspace. This increments intake_version; require explicit confirmation.

Input parameters:

- `confirm_replace` (boolean, required)
- `intake` (object, required)
- `project_id` (string, required)
- `project_key` (string, required)

### `workspace_run_intake` (~64 tokens)

Call canonical MCP project_intake for the stored intake and persist the returned run/version in Project Workspace. Requires confirmation because it stores a new run.

Input parameters:

- `confirm_store_run` (boolean, required)
- `project_id` (string, required)
- `project_key` (string, required)

### `workspace_add_evidence` (~102 tokens)

Append a PII-free evidence reference/status/hash/metadata record to Project Workspace. File bytes are not stored. Human verification is separate.

Input parameters:

- `confirm_store` (boolean, required)
- `evidence_status` (string, required)
- `evidence_type` (string, required)
- `metadata` (object)
- `project_id` (string, required)
- `project_key` (string, required)
- `sha256` (string|null)
- `source_ref` (string|null)

### `workspace_review_readiness` (~48 tokens)

Read design-review blockers, evidence gates, red flags and commissioning readiness. Completeness never equals human engineering approval.

Input parameters:

- `project_id` (string, required)
- `project_key` (string, required)

### `workspace_get_handoff` (~56 tokens)

Read the structured project handoff: latest stored intake run, evidence matrix, decisions already made by private reviewer, decision-memo seed and commissioning checklist.

Input parameters:

- `project_id` (string, required)
- `project_key` (string, required)

### `workspace_rotate_key` (~64 tokens)

Rotate the Project Workspace capability key. Destructive to the old key; require explicit confirmation. The new key is shown once and is never stored by MCP.

Input parameters:

- `confirm_rotate` (boolean, required)
- `project_id` (string, required)
- `project_key` (string, required)

### `workspace_prepare_quote_handoff` (~66 tokens)

Prepare a PII-free quotation handoff from the current Project Workspace state. Read-only: creates no link and submits nothing. Returns a deterministic confirmation_code and preserves engineering HOLD/RED FLAG context.

Input parameters:

- `project_id` (string, required)
- `project_key` (string, required)

### `workspace_create_quote_handoff` (~95 tokens)

After explicit user confirmation of workspace_prepare_quote_handoff, create a temporary PII-free /q/ short link that opens the existing official Taminyaran quotation form. The user enters contact details in the form. This creates NO RFQ/inbox record by itself.

Input parameters:

- `confirmation_code` (string, required)
- `confirmed` (boolean, required)
- `project_id` (string, required)
- `project_key` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/saeedfaai-taminyaran-engineering/mcp#diagnostics

## Score history

- 2026-11-05: 64
- 2026-11-04: 64
- 2026-11-03: 63
- 2026-11-02: 63
- 2026-11-01: 62
- 2026-10-31: 62
- 2026-10-30: 59
- 2026-10-29: 54
- 2026-10-28: 60
- 2026-10-27: 60

## Common questions

### What is the Taminyaran Engineering MCP server?

Taminyaran Engineering MCP is listed in the public MCP registry as io.github.saeedfaai/taminyaran-engineering. Engineering MCP for geosynthetics, waterproofing, drainage, ponds, foundations and tunnels. This page covers its hosted endpoint (https://mcp.taminyaran.com/mcp).

### Is the Taminyaran Engineering MCP server safe to use?

Taminyaran Engineering MCP scores 64 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 Taminyaran Engineering MCP server expose?

Taminyaran Engineering MCP exposes 42 tools: describe_capabilities, search_materials, get_material, design_project, project_intake, and 37 more. Their descriptions and schemas cost roughly 2,800 tokens of context every time the server is loaded.

### Does the Taminyaran Engineering MCP server require authentication?

No. We connected to Taminyaran Engineering MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Taminyaran Engineering MCP server still maintained?

Taminyaran Engineering MCP 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.

## Links

- Remote endpoint: https://mcp.taminyaran.com/mcp
- Website: https://mcp.taminyaran.com/
- Changelog RSS feed: https://verifymcp.io/servers/saeedfaai-taminyaran-engineering/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/saeedfaai-taminyaran-engineering/mcp.json
- HTML version of this page: https://verifymcp.io/servers/saeedfaai-taminyaran-engineering/mcp