What can you do with this server?

This server provides AI agents with structured access to a curated directory of 12,338 US addiction treatment facilities sourced from SAMHSA, enabling facility discovery and research across all 50 states. Here's what you can do: * Search for treatment facilities: Find addiction treatment centers by US state (required), city, treatment type (e.g., Inpatient Rehab, Detox, IOP, PHP, MAT, Counseling, Sober Living, Outpatient), and insurance accepted (e.g., Medicaid, Medicare, Aetna, Blue Cross, Private Pay). Results include facility names, locations, programs, insurance info, phone numbers, and browse URLs. * Get detailed facility profiles: Retrieve the full profile of a specific facility by name, including address, phone, programs offered, insurance plans accepted, SAMHSA verification status, and a direct browse URL. * List states with coverage: Get all US states (+ DC) that have facility data along with per-state facility counts — useful for exploring coverage before searching. * Look up treatment type definitions: Get detailed explanations of all treatment program types (duration, intensity, typical fit) to help understand which treatment type to search for.

GTH Intelligence - Substance Abuse Treatment Finder

by Crindo2

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

GTH Intelligence - Substance Abuse Treatment Finder

An MCP server that gives AI agents access to 12,338 curated US addiction treatment facilities, sourced from SAMHSA, across all 50 states. Built for treatment operators, healthcare AI developers, and anyone building tools that help people find care.

What It Does

The GTH Intelligence MCP server provides structured access to GetTreatmentHelp's directory of addiction treatment facilities -- enriched with descriptions, phone numbers, websites, programs offered, and insurance accepted.

Related MCP server: GPH Intelligence - Healthcare Vendor Finder

Tools

`search_facilities`

Search for addiction treatment facilities. Filter by US state (required), city, treatment type, and insurance accepted. Returns facility names, locations, programs, insurance, phone numbers, and a browse URL.

Parameters:

state (required) -- US state name or two-letter abbreviation (e.g. "California" or "CA")
city -- City name (partial match supported)
treatment_type -- One of: Inpatient Rehab, Outpatient, Detox, IOP (Intensive Outpatient), PHP (Partial Hospitalization), MAT (Medication-Assisted Treatment), Counseling, Sober Living
insurance -- Insurance provider accepted (e.g. "Medicaid", "Aetna", "Medicare")
limit -- Max results to return (1-20, default 5)

`get_facility_detail`

Get the full profile of one treatment facility by name: location, phone, programs offered, insurance accepted, and a browse URL. Partial name matching supported.

Parameters:

name (required) -- Full or partial facility name

`list_states`

List every US state with treatment facility data, with per-state facility counts.

`get_treatment_types`

Get definitions of all treatment program types (Inpatient Rehab, Detox, PHP, IOP, Outpatient, MAT, Counseling, Sober Living) with duration, intensity, and typical fit.

Usage

MCP Endpoint

https://gth-mcp-server.pages.dev/mcp

Connect via Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "gth-intelligence": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://gth-mcp-server.pages.dev/mcp"]
    }
  }
}

No API key required.

Data Coverage

12,338 curated addiction treatment facilities, sourced from SAMHSA
All 50 states + DC
Programs, insurance accepted, phone numbers, and browse links per facility
Monthly data refreshes from SAMHSA

Use Cases

Help people find nearby treatment options
Build facility-finder features into healthcare apps
Power competitive intelligence tools for treatment operators
Research treatment availability by geography or program type

API Access

Free: 100 calls per IP per day, no API key required.

For higher-volume access, get in touch via gettreatmenthelp.com/api-access/

Troubleshooting

No results returned -- state is required for search_facilities, so make sure it is set; then broaden by removing the city/treatment_type/insurance filters or trying a different state. Call list_states to see where coverage exists.
HTTP 429 (rate limited) -- the free tier allows 100 calls per IP per day, resetting at 00:00 UTC. For higher volume, see API Access above.
Can't connect -- point your client at the remote endpoint, no API key required:
```
npx -y mcp-remote https://gth-mcp-server.pages.dev/mcp
```
403 from a browser -- the /mcp endpoint validates the Origin header to prevent DNS rebinding. Standard MCP clients (Claude Desktop, mcp-remote, server-to-server) send no Origin header and connect fine; only disallowed browser origins are blocked.
Support -- questions or higher-volume access requests: cbeggroup@gmail.com

License

MIT

Available Tools

4 tools

get_facility_detailGet Facility DetailA

Read-onlyIdempotent

Inspect

Get the full profile of one specific treatment facility: address, phone, programs offered, insurance plans accepted, SAMHSA verification status, and a direct browse URL. Supports partial name matching — returns the best match if multiple facilities contain the query string. Use after search_facilities when the user wants to drill into a named facility.

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes	Full or partial facility name (e.g. 'Betty Ford' or 'Hazelden Betty Ford Center')

TDQS

A4.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, reducing the burden. The description adds valuable behavioral nuance: 'Supports partial name matching — returns the best match if multiple facilities contain the query string.' This is beyond the annotations, though 'best match' is slightly vague about tie-breaking.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no waste. The first sentence states the core purpose and deliverables, the second explains matching behavior, the third places it in the workflow. Information is front-loaded and each sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, read-only, no-output-schema tool, the description covers the purpose, content, matching behavior, and usage context. With annotations handling safety and idempotency, nothing essential is missing for the agent to select and invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description enriches the 'name' parameter with matching semantics ('Supports partial name matching — returns the best match if multiple facilities contain the query string'), which is not fully expressed in the schema. It explains the behavior, not just the type/format, adding value over structured fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Get the full profile of one specific treatment facility' and enumerates exact contents (address, phone, programs, insurance, SAMHSA status, browse URL). It explicitly distinguishes itself from search_facilities by specifying drill-down intent, making it unmistakable among siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit usage context: 'Use after search_facilities when the user wants to drill into a named facility.' This tells the agent exactly when to invoke it and implicitly when not to (i.e., not for searching or listing). It names the alternative tool, satisfying the top guideline bar.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_treatment_typesGet Treatment Type DefinitionsA

Read-onlyIdempotent

Inspect

Get definitions of all treatment program types (Inpatient Rehab, Detox, PHP, IOP, Outpatient, MAT, Counseling, Sober Living) with duration, intensity, and typical fit. Returns markdown-formatted explanations. Use when the user is uncertain which treatment_type to pass to search_facilities, or asks 'what's the difference between X and Y'.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds useful behavioral context by stating the return format ('markdown-formatted explanations') and that it covers 'all' types. This goes beyond annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose and action, no redundant phrasing. Every word contributes meaning, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description clarifies what the user gets: definitions, duration, intensity, typical fit, and specific program types. This is complete for a zero-parameter reference tool and requires no further elaboration.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is nothing for the description to add. The baseline for no parameters is 4, and the description correctly omits any parameter details since none exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb ('Get definitions') and clear resource ('all treatment program types'), enumerating the specific types. It also implicitly distinguishes from sibling tools like search_facilities by focusing on definitions rather than facility lookup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use the tool: 'Use when the user is uncertain which treatment_type to pass to search_facilities, or asks 'what's the difference between X and Y'.' This provides direct decision guidance and implies the alternative (search_facilities) without needing to name it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_statesList States with CoverageA

Read-onlyIdempotent

Inspect

List every US state that has treatment facility data in this directory, with per-state facility counts. Returns an array of {state, stateAbbr, count}. Use as a first step when the user's location is unclear, or to discover where coverage exists before calling search_facilities.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the description adds complementary value by disclosing the return shape ('array of {state, stateAbbr, count}') and the fact that it lists only states with data. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the primary action, then return format, then use case. No filler words; every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter listing tool, the description fully conveys the return format and intended usage context. It is self-contained and sufficient for an agent to invoke the tool correctly without additional information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description adds the output structure, which is the only relevant semantic detail. No parameter explanations are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'List every US state that has treatment facility data in this directory, with per-state facility counts.' It uses a specific verb ('List') and resource ('every US state'), and the scope ('with per-state facility counts') distinguishes it from siblings like search_facilities and get_facility_detail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'Use as a first step when the user's location is unclear, or to discover where coverage exists before calling search_facilities.' It also names the alternative tool (search_facilities), providing clear decision guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_facilitiesSearch Treatment FacilitiesA

Read-onlyIdempotent

Inspect

Search the 12,338 curated, SAMHSA-sourced US addiction treatment facility directory by state, city, treatment type, and insurance. Returns matched facilities with name, city/state, programs offered, insurance accepted, phone, and browse URL. Use this to find candidates — then call get_facility_detail for one facility's full profile. If the user is uncertain about location coverage, call list_states first.

ParametersJSON Schema

Name	Required	Description
`state`	Yes	US state name or 2-letter abbreviation (e.g. "California" or "CA"). Required — searches are scoped to one state at a time.
`city`	No	City name (partial match supported — 'san fran' matches 'San Francisco')
`treatment_type`	No	Type of treatment program. Call get_treatment_types if the user is unsure which applies.
`insurance`	No	Insurance provider accepted (e.g. "Medicaid", "Aetna", "Blue Cross", "Medicare", "Private Pay"). Partial match supported.
`limit`	No	Max results to return (1-20, default 5)

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds valuable context about the curated directory size and specifies the exact return fields, which goes beyond the schema. It lacks details on pagination or error handling, but the annotations lower the bar, and the added context earns a 4.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earns its place: the first defines the directory and filters, the second lists return fields, and the third gives usage flow with sibling tools. Highly concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the read-only/idempotent annotations and a fully descriptive schema, the description covers purpose, return fields, sibling tool flow, and prerequisite conditions. It provides enough context for an agent to select and invoke the tool correctly, even without an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters have detailed descriptions with types, defaults, and examples. The tool description recaps search dimensions but adds no new semantics beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action ('Search') on a specific resource ('12,338 curated, SAMHSA-sourced US addiction treatment facility directory') with identifiable filters (state, city, treatment type, insurance). It also distinguishes itself from siblings by explicitly directing to get_facility_detail for full profiles and list_states for location coverage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance is provided: 'Use this to find candidates — then call get_facility_detail for one facility's full profile.' It also instructs when to call list_states first if location coverage is uncertain. This clearly states when to use the tool versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesJun 20, 2026
- First observedget_facility_detail
- First observedget_treatment_types
- First observedlist_states
- First observedsearch_facilities

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.7/5.0

Scored 2026-06-20 00:20 across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: listing states, searching facilities, getting facility details, and explaining treatment types. No overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case (e.g., list_states, search_facilities).

Tool Count5/5

Four tools is ideal for a directory finder: coverage discovery, search, detail, and terminology help. Each tool earns its place.

Completeness5/5

The set covers the full workflow: discover coverage (list_states), search with filters (search_facilities), retrieve full profile (get_facility_detail), and understand program types (get_treatment_types). No obvious gaps.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

SAMHSA Treatment Locator
com.olyport
Find substance abuse and mental health treatment facilities
Government Data Health & Wellness Search
2
ChooseHelp Treatment Directory A
com.choosehelp
Editorially independent addiction & mental-health directory — facilities, therapists, expert Q&A.
Health & Wellness Search
91
GPH Intelligence - Healthcare Vendor Finder A
io.github.Crindo2
Find 76,000+ curated healthcare service vendors across 25 categories and all 50 US states.
Health & Wellness Search Research & Data
42
Bezal — Local Business Intelligence for AI Agents A
ai.bezal
Search 7,000+ local service businesses across America by category, location, or keyword.
Search E-commerce & Retail Location Services
132

Related MCP Servers

rollin-mcp-server
Search Location Services
DavidSirota
A
license
A
quality
C
maintenance
Wheelchair accessibility data for 105,000+ locations across 15 US states. Enables search, details, and feedback submission through natural language.
Updated a month ago (2026-08-22 01:17 UTC)
5
50 npm
1
MIT
GPH Intelligence - Healthcare
Search
Crindo2
A
license
A
quality
B
maintenance
Find 76,000+ curated healthcare service vendors across 25 categories and all 50 US states. Search by category, specialty, city, state, and EHR system to identify billing, credentialing, EHR, and practice-consulting vendors that serve medical practices.
Updated 3 days ago (2026-09-16 21:54 UTC)
3
MIT
Formulary MCP Server
Biology & Medicine Government Data
openpharma-org
F
license
Not graded
quality
C
maintenance
Provides unified access to drug formulary data from US ACA marketplace health insurance plans, enabling drug search, coverage details, restriction info, and plan comparison across thousands of plans.
Updated 9 months ago (2025-12-22 17:50 UTC)
-
GLP1Search MCP Server
Health & Wellness Search Biology & Medicine
Sndevore77
A
license
Not graded
quality
C
maintenance
Enables searching and comparing GLP-1 medication providers, medications, side effects, and FAQs across a directory of 18,344 US clinics, telehealth programs, and pharmacies.
Updated 2 months ago (2026-07-30 18:37 UTC)
28 npm
MIT

GTH Intelligence - Substance Abuse Treatment Finder

What It Does

Tools

search_facilities

get_facility_detail

list_states

get_treatment_types

Usage

MCP Endpoint

Connect via Claude Desktop

Data Coverage

Use Cases

API Access

Troubleshooting

Links

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

`search_facilities`

`get_facility_detail`

`list_states`

`get_treatment_types`