habari-mcp
habari-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 habari-mcp · Use with any MCP client.
MCP server for Kenya civic information — Kenya Gazette, government tenders, open data, parliament tracker, citizen feedback channels. 5 tools.
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
Related MCP server: elimu-mcp
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 toolscitizen_feedback_channelsC
Official channels for Kenyan citizen feedback, complaints, and government access. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| issue_type | Yes |
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 must convey behavior. It only mentions 'DEMO,' implying it may be non-functional or sample data, but does not clarify whether the tool reads data, returns a list, or requires authentication. Behavioral traits are not disclosed.
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 sentence, which is concise. However, it lacks structure (e.g., bullet points or sections) and omits essential details, making it under-specified rather than efficiently brief.
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 lack of annotations and the single parameter with no schema description, the tool is incomplete. The output schema exists but is not described in the description. The sibling tools indicate a contextual domain, but the description fails to provide enough information for correct 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 only parameter, issue_type, is a required string with no description, enum, or format. The tool description mentions 'feedback, complaints' but does not map issue_type to these categories or suggest valid values. Schema description coverage is 0%, so the description should compensate, but it does not.
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 states it provides 'official channels for Kenyan citizen feedback, complaints, and government access,' which clearly identifies the domain. It distinguishes from sibling tools (e.g., gazette_search, parliament_tracker) that cover different topics. However, 'channels' is somewhat vague and does not specify the tool's output (e.g., list, details).
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 is provided on when to use this tool versus alternatives, such as open_data_guide or parliament_tracker. There are no instructions on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
gazette_searchD
Guide to searching Kenya Gazette for legal notices, regulations, and appointments. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| date_range | No | ||
| search_type | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose what happens when called. 'DEMO' suggests it might not perform real searches, but this is ambiguous.
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 just one sentence, but it includes the unhelpful 'DEMO' and lacks essential details. Conciseness without substance is not valuable.
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?
Despite having an output schema, the description fails to explain the tool's behavior or results. It is incomplete for a search tool, leaving major gaps.
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 coverage is 0%, and the description does not explain any parameter. 'search_type' and 'date_range' are not described at all, leaving the agent clueless about valid inputs.
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 says 'Guide to searching Kenya Gazette... DEMO', but it's unclear whether this tool actually performs a search or merely provides guidance. The term 'DEMO' further obscures its functionality.
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 use this tool versus sibling tools like 'citizen_feedback_channels' or 'tender_search_guide'. The description lacks any context for decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
open_data_guideC
Kenya open government data sources and APIs. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| data_type | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Only says 'DEMO', implying it is non-functional or a prototype, but no disclosure of side effects, data access, or reliability.
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?
Extremely short but not well-structured. 'DEMO' is uninformative. Could be more concise while adding key details.
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?
Tool has one parameter and an output schema, but description is too brief to understand what the tool actually returns. Incomplete for an agent to use effectively.
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 coverage is 0% and description does not explain the 'data_type' parameter. No hint about expected values or format.
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?
Description states it deals with 'Kenya open government data sources and APIs', which gives a general purpose but lacks specificity (e.g., list, search, or retrieve). 'DEMO' adds ambiguity. It distinguishes from siblings as a guide, but the verb is missing.
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 use this tool versus alternatives like citizen_feedback_channels or gazette_search. No context on use cases or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
parliament_trackerC
Track Kenya parliament: bills, Hansard, committees, and petitions. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| query_type | Yes |
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 must carry the full burden. It only says 'Track... DEMO' without disclosing whether operations are read-only, any authentication needs, rate limits, or what happens on use. The 'DEMO' label is ambiguous.
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 (one sentence) but lacks essential details. It does not earn its place by providing key information beyond a minimal statement of purpose. Front-loading is not relevant when content is so sparse.
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 lack of annotations, a single undocumented parameter, and only a minimal purpose statement, the description is wholly inadequate. An output schema exists but is not described. The tool as defined does not provide enough information for an agent to 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 required parameter (query_type) with no description or enum. Schema description coverage is 0%. The description does not explain what values query_type accepts or how it relates to the listed items (bills, etc.).
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 states the tool's purpose: tracking Kenya parliament with specific entities (bills, Hansard, committees, petitions). It distinguishes from sibling tools which cover citizen feedback, gazette, open data, and tenders.
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 is provided on when to use this tool versus alternatives, nor any context for when it is appropriate. The description only lists what it tracks, with no mention of prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
tender_search_guideC
Guide to finding and accessing Kenya government tenders. DEMO.
| Name | Required | Description | Default |
|---|---|---|---|
| county | No | ||
| sector | 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 provided, so description carries full burden. It discloses no behavioral traits such as side effects, authentication needs, or data returned. The short description is insufficient for transparency.
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 very concise (two clauses), but conciseness comes at the cost of clarity. It lacks essential details, making it inadequate rather than efficient.
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?
Despite having an output schema (context indicates 'Has output schema: true'), the description does not mention what the tool returns or how it functions. The DEMO label and missing parameter info make it incomplete for a 2-parameter tool.
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?
With 0% schema description coverage, the description must explain parameters but fails to do so. The two optional parameters (county, sector) are not mentioned or defined.
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 states it is a guide to Kenya government tenders, which gives a general purpose. However, it does not specify the exact action (e.g., search, list, provide instructions) and includes 'DEMO', adding ambiguity about its real functionality.
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 use this tool versus sibling tools (e.g., gazette_search, open_data_guide). The description only indicates domain but lacks context for selection.
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. Dates show when Glama detected each change.
5 tool updates
v0.1.1- First observed
citizen_feedback_channels - First observed
gazette_search - First observed
open_data_guide - First observed
parliament_tracker - First observed
tender_search_guide
TDQS
Each tool targets a distinct area of Kenyan government information: citizen feedback, gazette legal notices, open data, parliament tracking, and tenders. No overlap or ambiguity.
All names use snake_case and are descriptive of their purpose (e.g., gazette_search, parliament_tracker). However, the pattern varies slightly (some end with '_guide', '_search', '_tracker', '_channels'), lacking a single consistent verb_noun structure.
Five tools is an appropriate and focused scope for a server covering key aspects of Kenyan government access. Not too sparse or overwhelming.
The set covers major access points (feedback, legal notices, open data, parliament, tenders). Minor gaps like government directory or press releases exist but don't undermine the core functionality.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
TED MCP Server: Real-time EU public tenders access. https://www.lexsocket.ai/
Government tenders, awards and pre-tender pipelines from 21 official sources as MCP tools.
Open Contracting MCP — international public procurement: government tenders
Related MCP Servers
- AlicenseCqualityAmaintenanceMCP server for Kenya environment — NEMA permits, climate data, conservation areas, environmental rights, climate adaptation.5MIT
- AlicenseAqualityAmaintenanceMCP server for Kenya education — school registry, KCSE/KCPE results, HELB student loans, TVET programs, literacy resources.5MIT
- AlicenseBqualityAmaintenanceMCP server for Kenya transport — matatu route finder, NTSA services, boda licensing, freight logistics, passenger rights.5MIT
- AlicenseBqualityAmaintenanceMCP server for Kenya health system — NHIF/SHA coverage, facility finder, community health workers, maternal health guidance, essential medicines.6MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gabrielmahia/habari-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server