Skip to main content
Glama

Server Details

Open-source API specs for African providers (payments, SMS, KYC, delivery) for AI agents.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
afrotools/afrotools
GitHub Stars
32
Server Listing
Afro Tools MCP Server
ChatGPT
–
Claude
afro.tools

TDQS

A4.6/5.0

Scored across 5 tools

Disambiguation4/5

Each tool has a clear role: discovery (list_providers, search_specs), retrieval (get_spec), and feedback (report_integration, request_spec). The only real overlap is list_providers vs. search_specs, since an unfiltered search returns much the same listing, but the descriptions explicitly steer usage (search first, list for categories/accounts) and the feedback tools are clearly split between 'request a missing spec' and 'report an existing spec's result'.

Naming Consistency5/5

All five names follow a consistent verb_noun snake_case pattern (get_spec, list_providers, search_specs, report_integration, request_spec). No mixed casing or stray verb styles.

Tool Count5/5

Five tools is well-scoped for a spec registry: discovery, retrieval, and two feedback paths. Nothing feels redundant enough to remove and there is no filler.

Completeness4/5

The surface covers the full lifecycle an agent needs: find providers (list/search), fetch the spec, request missing specs, and report results that feed verification. The only minor gap is no direct 'list capabilities for a provider' operation, though provider-filtered search and the available_capabilities error payload largely cover it.

Available Tools

5 tools
get_specGet SpecA
Read-onlyIdempotent
Inspect

Returns the full spec payload for a provider + capability, including canonical_example.ts source code. Use this to get the complete integration guide — auth pattern, endpoint, schemas, gotchas, and a TypeScript example — before writing API calls.

The response includes a "status" field:

  • "verified": tested against the provider's API, in "sandbox" or "production" (verified_in / verification.environment)

  • "deprecated": the provider is retiring it — "deprecation" gives the reason, replaced_by (the capability to use instead) and removed_after

  • anything else (e.g. "ready", "unverified"): written from the provider's documentation, NOT tested against the live API "verification" says how and when it was tested; sandbox proves the request and response shapes, not production behaviour. "open_questions", when present, lists what the provider's docs do not answer: tell the user before relying on the spec. "account", when present, says who can open the provider's account; list_providers and search_specs add its open questions (caps, conditions) and sources. "environments", when present, gives each documented environment's base URL; a missing one is undocumented — ask the user, never guess. "auth.credentials" / "signing" / "token_exchange" / "apply" and "webhook.signature", when present, describe the auth and webhook signature steps exactly: follow them. "parameters", when present, lists the path, query and header parameters; "input_schema" is the request body only. A path parameter fills the {name} placeholder of endpoint.url. "success_condition", when present, names the response field (dotted path) that says the call succeeded: a 2xx response with another value is a failure.

If status is not "verified", always warn the user before generating integration code: "This spec has not been tested against the live API yet and may contain errors."

Args:

  • provider (string): Provider slug e.g. "paycard"

  • capability (string): Capability name e.g. "create_payment"

  • variant (string[]?): Discriminator values to keep, e.g. ["mobile_money_ghs"] or ["bank", "NGN"]. In every union (oneOf) of input_schema and response_schema, only the branches pinned to one of these values are kept; a union none of them matches is left whole. Without it, all branches are returned. The response lists every value under "variants" (discriminator property → values). A large spec also carries "_mcp_size_note": if your client cut the result, call again with the variant you need.

Returns: Full Spec object with canonical_example string (plus _mcp_warning when status is not "verified"). If not found: isError, with { error, available_capabilities } when the provider exists — capability names are each provider's own, pick one from that list — and did_you_mean (closest provider slugs or capability names) when one is close. A capability removed from the registry after a provider deprecation answers isError with removed_in, reason and alternatives. Use search_specs or list_providers first to discover available providers and capabilities.

Inputs: provider (required), capability (required), variant.

list_providersList ProvidersA
Read-onlyIdempotent
Inspect

Lists every provider in the registry with what it offers. Every listed provider is AI Ready: its specs give you a structured description to integrate it from (endpoints, fields, errors, gotchas taken from the provider's docs). verified_count says how many of its capabilities were also tested against the provider's API; all_verified is true when all of them were. When you show this list, present what each provider offers and give the tested capabilities per provider (e.g. "3/4 tested"), not a headline such as "only one provider is fully verified": a capability not tested yet is still documented and usable, it may contain errors. Before integrating one, check its "status" with get_spec and tell the user if it was not tested.

"account", when present, says who can open the account the API needs, from the provider's own pages: holder is "business_only" (a registered business) or "business_or_individual", for all its countries except those in country_exceptions; documents lists what the pages ask for; open_questions gives caps, conditions and what the pages leave unsaid — tell the user, they can change the answer; sources link to those pages (with checked_at, the reading date). A country with no answer (no holder, not in country_exceptions), or no "account" at all, is not documented: tell the user to check with the provider before signing up, never guess.

note is present when the list was trimmed to stay readable: description first, then the accounts' sources and checked_at (each provider's page on afro.tools shows the description, links the sources and gives the date) — never an account's answers or open questions. It says which.

Returns: { note?, providers: Array<{ slug, name, category, channels?, all_verified, verified_count, capabilities, country_code, docs_public, docs_url, description?, account? }> }

Inputs: no named parameters.

report_integrationReport IntegrationA
Read-onlyIdempotent
Inspect

Builds a pre-filled GitHub link to report how an integration went against a spec — it worked, or the spec is wrong. Call it when the user confirms an integration works against the real API (sandbox or production), or when you find the spec does not match the API. Reports are how specs get verified and fixed. Nothing is posted: the user reviews the text and submits it on GitHub. One report per provider, covering every capability of the flow (e.g. payment init, status, webhook): each one is verified on its own.

Args:

  • provider (string): Provider slug e.g. "paycard"

  • capabilities (array): Every capability the integration used, each with its own result e.g. [{ "capability": "create_payment", "result": "worked" }, { "capability": "webhook", "result": "wrong: status is SUCCESSFUL, spec says succeeded" }]

  • summary (string): One line about the flow, e.g. "checkout flow works in sandbox"

  • details (string): What was called, what came back, what differed from the spec. NEVER include API keys, tokens, phone numbers or personal data.

  • tested_on (string?): Date of the test, YYYY-MM-DD

Returns: { url, next_step } — give the url to the user and follow next_step. If a spec does not exist: isError, with { error, available_capabilities } when the provider exists.

Inputs: details (required), summary (required), provider (required), capabilities (required), +1 more.

request_specRequest SpecAInspect

Logs a request for a spec that doesn't exist yet and notifies maintainers. Call this when a user asks for a provider or capability that has no spec in the registry (check list_providers first), or needs a capability in a country where no listed provider offers it (search_specs with country first). This helps maintainers prioritize which specs and providers to add next.

Args:

  • capability (string): Capability name e.g. "create_payment", or what is needed e.g. "ussd"

  • provider (string?): Provider slug e.g. "wave" — omit when no provider is named

  • country_code (string?): ISO 3166-1 alpha-2 code e.g. "SN" — required when provider is omitted

  • follow_up ("none" | "github_issue", default "none"): "none" records the request only; "github_issue" also returns issue_url, a pre-filled GitHub issue the user can review and submit

Returns: { logged: true, count, issue_url? } if the request was recorded — count is the all-time number of times this provider + capability (or, without a provider, capability + country) was requested, including this one (a repeated request counts again). count is absent if it could not be determined: do not guess a number. issue_url only with follow_up "github_issue": give it to the user, who submits it. { logged: false, reason: "spec already exists" }: the spec is in the registry — use the existing spec (get_spec) instead. isError if the request could not be stored: tell the user it was NOT recorded.

Inputs: capability (required), provider, follow_up, country_code.

search_specsSearch SpecsA
Read-onlyIdempotent
Inspect

Searches specs by words and filters by category, channel, provider, country, currency, status or capability type. Returns the matching providers, each with its countries, currencies, sandbox flag, docs URL and the matching capabilities (name, type, status, example_prompt) — no endpoints, schemas, gotchas or canonical_example source. Use get_spec with the exact capability name to retrieve the full payload. A capability with "variants" has several request/response shapes (e.g. one per payment method or corridor): pass the ones you need to get_spec "variant" to receive only those.

Each result includes a "status" field:

  • "verified": tested against the provider's API, in "sandbox" or "production" (verified_in / verification.environment)

  • "deprecated": the provider is retiring it — get_spec says what replaces it

  • anything else (e.g. "ready", "unverified"): written from the provider's documentation, NOT tested against the live API — may contain errors

Always check the status field. If status is not "verified", inform the user that the spec is experimental and may contain errors.

Args:

  • query (string?): Words, e.g. "wave", "mobile money senegal", "send sms", "kyc", "XOF". Every word must match somewhere: provider name or slug, capability, description, example_prompt, countries (code or English/French name), currencies, channels (a few synonyms: momo, otp, kyc, payout…). Providers the query names come first.

  • category (string?): Filter by category, e.g. "payment", "communications" (SMS, WhatsApp, USSD, voice and email providers — "sms" is accepted as a legacy alias), "identity" (KYC, document verification, AML), "logistics" (delivery and courier providers). The registry adds categories over time: list_providers shows every category that exists

  • channel ("sms"|"whatsapp"|"ussd"|"voice"|"email"?): Only providers that offer this channel

  • provider (string?): Provider slug e.g. "paycard"

  • country_code (string?): ISO 3166-1 alpha-2 e.g. "GN"

  • currency (string?): ISO 4217 e.g. "XOF"

  • status ("verified"|"ready"|"unverified"?): e.g. "verified" for specs tested against the provider's API

  • capability_type ("synchronous"|"asynchronous"|"webhook"|"sdk"?): Filter by capability type

Returns: { providers: ProviderMatch[], note?: string, hint?: string, unverified_count: number, warning?: string } Each provider may carry "account": who can open its account, with its open questions (see list_providers, which also has the sources). note is present when a wide result was trimmed to stay readable: example_prompt first, then variants, then the whole account (never an account's answers without its open questions) — it says which; call list_providers for the accounts, get_spec for the variants. hint is present when nothing matched: widen the search before telling the user a provider is unavailable. unverified_count counts matching capabilities whose status is not "verified"; warning is present only when it is > 0.

Inputs: query, status, channel, category, +4 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Open-source MCP server that streamlines payment integration for AI agents and financial apps in Africa, providing unified tools for providers like M-Pesa.
      1
      -
    • -
      license
      Not graded
      quality
      Not graded
      maintenance
      Field operations agent API for task management, geo-tracking, and team coordination. Built for African logistics, delivery, and field service teams.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Nigeria's AI infrastructure server that provides business automation agents including WhatsApp automation, university support, travel management, and legal document processing. Integrates payment processing, text-to-speech capabilities, and webhook handling for Nigerian businesses.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      A unified MCP server for West African payment providers, enabling AI agents and REST clients to initiate payments, payouts, refunds, and manage webhooks across 10 providers with a single API.
      8
      22 npm
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.