afya-ya-akili-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@afya-ya-akili-mcpFind a therapist in Nairobi county"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
afya-ya-akili-mcp
Compatible with claude-sonnet-5 (released 2026-06-30) — Anthropic's most agentic
Sonnet yet. Runs multi-step tool chains end-to-end without stopping short.
Install: pip install afya-ya-akili-mcp · Use with any MCP client.
Kenya mental health via MCP — therapist finder, crisis lines, rights, workplace wellness
Install
pip install afya-ya-akili-mcpRelated MCP server: tafsiri-mcp
What it does
5 MCP tools covering Kenya mental health resources. 1st world equivalent: BetterHelp / Mind UK.
Tool | Description |
| Licensed mental health practitioners by county |
| Kenya crisis lines — Befrienders Kenya 0800 723 253 |
| Rights under Kenya Mental Health Act 2022 |
| EAP programs, occupational stress, OSHA |
| Online resources, support groups, self-care |
Usage
# Run as standalone MCP server
afya-ya-akili-mcp
# Or add to Claude Desktop / any MCP client
# Add to your MCP config: {"command": "afya-ya-akili-mcp"}Part of the Kenya Coordination Infrastructure Stack
This is one of 23 MCP servers covering the full coordination infrastructure of East Africa:
Economic: mpesa · mkopo · bima · soko · sifa · remit · kra · faida
Physical: wapimaji · nishati · usafiri · ardhi
Social: afya · afya-ya-akili · elimu · kazi · haki-ya-kazi · kilimo · jumuia
Civic: nyumba · habari · mazingira · civic-agent-kit
→ The Nairobi Stack
→ Full Portfolio
Trust Integrity
All data in this server is clearly labeled DEMO where synthetic. Verify all operational data with the relevant Kenyan government authority before use.
License
MIT © Gabriel Mahia | AI-KungFU | contact@aikungfu.dev
Decision infrastructure for East Africa
Part of the East Africa Coordination Stack
This MCP server is one of 32 tools in the Kenya coordination infrastructure.
Connect it to africa-coord-bus —
the coordination event bus that routes signals between domains automatically.
pip install africa-coord-busAll 32 servers: pypi.org/user/gmahia Live demo: coord-cascade-demo
IP & Collaboration
MIT licensed. Feedback via GitHub Issues only — pull requests are not accepted. Demo data is labeled DEMO and is not suitable for operational decisions. Full policy: docs/architecture/IP_POLICY.md. Security reports: see SECURITY.md.
Part of the East Africa coordination stack
Install & run:
pip install reli-cli && reli list— 33 MCP servers on the official MCP Registry underio.github.gabrielmahiaEvaluate any model on Swahili agent tasks: kipimo · dataset · leaderboard
Coordinate across servers: africa-coord-bus — offline-first event bus with a built-in Kenya routing table
Datasets: huggingface.co/gmahia · Docs hub: nairobi-stack
Model-agnostic by design: closed APIs, open-weight models, and small distilled models are all first-class citizens.
Available Tools
5 toolscrisis_line_directoryCrisis Line DirectoryB
Kenya mental health crisis lines and emergency resources. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. The "DEMO" tag does disclose that this is a demonstration resource, which hints at limited authenticity, but nothing is said about what the tool returns, whether the data is current, or the nature of the emergency resources. Minimal but non-zero disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One short sentence with the key scoping facts front-loaded. The "DEMO" suffix is slightly awkward but conveys important status information and doesn't add meaningful bloat for a zero-parameter tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The output schema covers return structure and there are no parameters, so the core calling contract is simple. However, the ambiguous DEMO status and the lack of any usage distinction from sibling mental-health tools leave an agent uncertain about when and how to rely on this directory.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema coverage, so the baseline is 4. The description adds value by specifying the content scope (Kenya, crisis lines, emergency resources), which is all the parameter-level meaning a no-parameter tool needs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"Kenya mental health crisis lines and emergency resources" clearly identifies the resource type, geographic scope, and domain, distinguishing it from siblings like mental_health_provider_finder (providers) and mental_health_rights (rights). The verb is implied rather than explicit but the intent is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to call this tool versus siblings. An agent cannot tell whether to use this over self_help_resources or mental_health_provider_finder for a given user need. The crisis/emergency framing implies urgency, but no explicit when/when-not criteria are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
mental_health_provider_finderMental Health Provider FinderB
Find licensed mental health practitioners in Kenya by county. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| county | No | ||
| provider_type | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds only 'DEMO,' which hints at a limited or non-production state, but does not explain the data source, verification of 'licensed' status, or any restrictions. 'Find' implies read-only behavior, but that is not made explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single front-loaded sentence that conveys the core purpose efficiently. The trailing 'DEMO' is vague but not verbose; there is no wasted wording beyond that.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Although the tool is simple with optional parameters and an output schema, the description still omits provider_type entirely and fails to clarify what 'DEMO' means for invocation or results. An agent can make a basic county-only call, but it is not fully equipped to use all inputs or understand limitations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate for both parameters. It explains county as a geographic filter ('by county') but says nothing about provider_type, leaving one of two parameters without semantic guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description begins with a specific verb and object: 'Find licensed mental health practitioners in Kenya by county,' which clearly states the tool's resource and scope. It is semantically distinct from sibling tools like crisis_line_directory and mental_health_rights, so an agent can tell them apart without opening schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when looking for licensed practitioners in a Kenyan county, but it does not explicitly state when to prefer this tool over alternatives or when not to use it. There is no sibling routing or exclusionary guidance, so the context is inferred rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
mental_health_rightsMental Health RightsC
Mental health rights under Kenya Mental Health Act 2022. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| topic | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only states the topic, not what the tool does (e.g., returns a summary, provides legal text, or offers guidance). The word 'DEMO' hints it may be a demonstration but does not clarify expected behavior, side effects, or data handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short, which could be seen as concise, but it is under-specified. It lacks essential information about functionality and parameters. It is not structured to front-load key details; it simply states the topic without elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Although an output schema exists and the tool has only one optional parameter, the description is too sparse to allow an agent to invoke it correctly. It does not explain what output is produced, how the topic parameter influences it, or what the tool returns. The presence of an output schema does not compensate for the absence of usage context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not mention the 'topic' parameter at all. There is no explanation of how this optional parameter affects results or what values are expected. The description fails to compensate for the schema's lack of parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the subject: mental health rights under a specific act (Kenya Mental Health Act 2022). It distinguishes itself from sibling tools like provider finder or crisis directory by focusing on rights rather than services. However, it lacks an explicit verb (e.g., 'get', 'list', 'explain'), so it reads more as a title than an action statement.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus the siblings. No mention of appropriate contexts, exclusions, or conditions. The description implies a user seeking rights information, but provides no explicit direction or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
self_help_resourcesSelf Help ResourcesC
Kenya mental health self-help resources and support groups. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| area | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states what the resource is and appends 'DEMO.' It does not disclose whether this returns a static list, supports search, has limitations, requires anything, or what the response contains. This is insufficient for an agent to predict tool behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief and front-loaded, which is good for scanning. However, the standalone 'DEMO.' adds little value and the overall text is more under-specified than concise; it saves words by omitting essential behavioral and parameter context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With one optional 'area' parameter, an output schema, and sibling tools providing some context, the tool is not highly complex. However, the description fails to explain how the 'area' parameter works, what the tool returns, or how this relates to sibling tools, so the agent cannot reliably use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter ('area') with 0% schema description coverageache, and the tool description does not mention or explain this parameter. The agent is left to guess whether 'area' is a geographic region, a topic area, or something else, especially given the Kenya-specific context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a clear resource ('Kenya mental health self-help resources and support groups'), and the geographic scope helps differentiate from sibling tools like crisis_line_directory or workplace_wellness_guide. However, it lacks an explicit verb indicating what the tool does (list? search? provide?). It is more of a content label than an action-oriented purpose statement.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus sibling tools such as mental_health_provider_finder or crisis_line_directory. The context is implied by the resource type, but no exclusions or alternative conditions are stated, leaving the agent to infer which tool fits a given user request.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
workplace_wellness_guideWorkplace Wellness GuideC
Kenya workplace mental health policies and EAP programs. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure, but it says nothing about whether this is a read-only lookup, what output shape to expect, or any limitations. The term 'Guide' suggests informational content and likely no side effects, but this is left to inference.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely brief and front-loaded with the core topic. The 'DEMO' suffix adds a minor note about its nature, but it is not entirely necessary for tool selection. Overall it is concise but not a model of structural richness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple schema and one optional parameter, the bar is low, yet the description still fails to explain how to invoke the tool responsibly—notably how to use the query parameter and what kind of answer an agent can expect. The topic alone is insufficient for confident invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single optional 'query' parameter has 0% schema description coverage, and the tool description never references it. There is no hint about what kind of query is expected (topic, keyword, location) or whether it is even needed to retrieve the guide, so an agent cannot confidently set a useful value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description identifies the domain as 'Kenya workplace mental health policies and EAP programs,' which distinguishes it from sibling tools like crisis_line_directory or provider_finder. However, it lacks an explicit verb stating what the tool actually does (e.g., 'provides,' 'searches,' 'searches for'), so the purpose is implied rather than explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no guidance on when to use this tool instead of the listed siblings, nor any exclusions or preferred query scenarios. The only extra signal, 'DEMO,' is ambiguous and does not convey usage context.
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.
5 tool updates
v0.1.3- First observed
crisis_line_directory - First observed
mental_health_provider_finder - First observed
mental_health_rights - First observed
self_help_resources - First observed
workplace_wellness_guide
TDQS
Scored across 5 tools
Each tool addresses a distinct aspect of mental health support in Kenya: provider search, crisis lines, legal rights, workplace policies, and self-help resources. There is no overlap in purpose, making selection unambiguous for an agent.
All tool names follow a consistent pattern of descriptive noun phrases in snake_case (e.g., mental_health_provider_finder, crisis_line_directory). The naming style is uniform and clearly conveys each tool's purpose.
With 5 tools, the server is well-scoped for a mental health resource directory. Each tool covers a distinct domain area, and the count is neither too sparse nor overwhelming for the intended purpose.
The tool surface covers the primary pillars of mental health support: finding providers, crisis intervention, legal rights, workplace wellness, and self-help. Minor gaps exist (e.g., specific condition resources or educational materials), but the core lifecycle of accessing mental health information is well represented.
Maintenance
Related MCP Connectors
Teen-first library on CBT, DBT, and finding the right therapist.
Chilean online mental-health clinic (Spanish): articles, professionals, availability, tests.
Find substance abuse and mental health treatment facilities
Check live availability and book therapy sessions with a Malayalam-speaking psychologist.
Related MCP Servers
- AlicenseCqualityAmaintenanceProvides tools for Kenyans abroad to navigate dual citizenship, diaspora taxes, homeland investment, document verification, and community resources via MCP.6MIT
- AlicenseCqualityAmaintenanceProvides translation and language resources for Kenyan languages including Swahili, Kikuyu, and Luo, with tools for glossaries, language guides, and civic terminology.619 PyPIMIT
- AlicenseCqualityAmaintenanceProvides tools to access information about religious institutions and community services in Kenya, including Catholic dioceses, Protestant denominations, Muslim communities, and welfare programs.625 PyPIMIT
- AlicenseBqualityBmaintenanceMCP server for Kenya housing — rental market guide, tenant rights, building permits, affordable housing programs, housing finance.5MIT