Claude
- Open Add custom connector ↗
- Name it Detectability and paste the URL
- Click Add, then ask away
https://detectability.mukreminnergiz.com/mcp
Mükremin Nergiz·Science & engineering·Live in ![]()
Pre-survey detectability
Detectability answers one question before fieldwork: will a geophysical survey detect a given buried target? It models five methods: gravity, magnetics, the magnetic vertical gradient (gradiometer), ground-penetrating radar (GPR) and electrical resistivity (ERT). Describe the target in plain language (a cave, void, tunnel, pipe, buried room, foundation, wall, dyke or geological contact), its depth and size, the material and the surrounding rock, and optionally the survey location. Detectability forward-models the response, computes the Earth's main field at the site from IGRF-14, and compares the signal with instrument and field noise. Gravity and magnetics are assessed unless another method is asked for.
The result card shows, for each method, a verdict (clearly detectable, marginal or not detectable), the signal, the noise, the signal-to-noise ratio, the recommended station spacing and profile length, the modelled profile and the main assumptions. A remanent magnetisation can be given, as a Koenigsberger ratio or as a vector; none is assumed. For radar, a material without radar properties in the tables is reported as not assessed rather than guessed. Resistivity in the assistant is the forward model only: the inversion, which shows whether the target is recovered, runs on the Detectability website, and every result links to the same case there. A Python script can be requested that recomputes a result with the open-source library.
The models are checked against closed-form limits, numerical integration, an independent code and the British Geological Survey's main-field values, with the results published on the website. Results are model-based expectations for survey planning; they do not replace site investigation. Detectability is open source (BSD-3-Clause), needs no account, and only reads and computes.
Can a gravity survey detect a 20 m wide air-filled cave whose top is 15 m deep in limestone near Sivas, Türkiye?
https://detectability.mukreminnergiz.com/mcphttps://detectability.mukreminnergiz.com/mcpdetectability.mukreminnergiz.comcaveCan a gravity survey detect a 20 m wide air-filled cave whose top is 15 m deep in limestone near Sivas, Türkiye?dykeIs a 5 m wide vertical basalt dyke in sandstone, from 2 m to 60 m depth, visible to a magnetometer at 39.75 N, 37.02 E?roomHow dense must my gravity stations be to find a buried 4 × 5 m room, 1 to 3 m deep, in clay?tunnelWould gravity or magnetics be better for finding a 3 m diameter tunnel at 3.5 m depth in basalt? The site is at 40.0 N, 32.9 E.The AI reads these server instructions before using this connector, every time.
Detectability answers one question before fieldwork: will a geophysical survey detect a given buried target? It models five methods: gravity, magnetics, magnetic gradient (gradiometer), ground-penetrating radar (GPR) and electrical resistivity (ERT). Use whenever the user describes a target (cavity, cave, void, tunnel, pipe, shaft, well, room, foundation, wall, dyke, fault or contact) and asks whether a survey could find it, which method to use, or how dense the stations must be.
How to call it:
Translate the description into a shape, depths and size in metres, the target material (air for an empty cavity, water for a flooded one) and the host material. Pick materials from the list; if the user gives measured values, pass them instead: density_contrast (kg/m^3), susceptibility_contrast (SI), permittivity and conductivity (GPR), resistivity (ERT).
methods: gravity and magnetic are run when none is named. Add "gradient", "gpr" or "ert" when the user asks about a gradiometer, ground radar or resistivity, or asks which method is best for a shallow target.
Magnetics and the gradient need the survey location (latitude, longitude) for the Earth's main field. If the user names a place, use its coordinates; if no place is known, ask, or leave those methods out.
Remanent magnetisation is not assumed for any material. Pass it only if the user gives it: either koenigsberger_ratio (Q), or remanence with remanence_inclination and remanence_declination, all three together.
None in the store listings or on the server
Pre-survey detectability. Detectability answers one question before fieldwork: will a geophysical survey detect a given buried target? It models five methods: gravity, magnetics, the magnetic vertical gradient (gradiometer), ground-penetrating radar (GPR) and electrical resistivity (ERT). It is listed under Science & engineering.
Open its listing in the app's connector directory and connect. No sign-in is needed. Step-by-step setup for each app is on this page.
The Detectability MCP server URL is https://detectability.mukreminnergiz.com/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.
Yes. Detectability is published or run by Mükremin Nergiz, so it is the official MCP server. See other official connectors.
It is listed in 1 store: ChatGPT. Apps where it is not listed can usually still add it as a custom connector.
It is ranked 12,698 of 15,293 in the ChatGPT directory. A rank is the store's own order, not a usage count. How we track ranks.
It has 3 tools: 3 read data. See every tool and its inputs.
No. All of its tools only read data.
None that we found. None in the store listings or on the server.
Here are examples from its store listing. Type one into your AI after you connect.
Yes. Some of its tools show an interactive widget in the chat, not only text. See more connectors with interactive UI.
The top-ranked connectors in Science & engineering include:
This page updates every day. To ask about Detectability from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.