Skip to main content
Glama

Nigeria Invoices (FIRS / NRS MBS e-invoicing IRN)

Server Details

Nigeria FIRS/NRS MBS e-invoicing for AI agents - validate, sign, confirm invoices (IRN + QR).

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.4/5 across 3 of 3 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool has a distinct purpose: create_invoice signs/submits, query_invoice looks up by IRN, and validate_invoice pre-validates. No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case (create_invoice, query_invoice, validate_invoice). No deviations.

Tool Count5/5

Three tools are well-scoped for the Nigeria e-invoicing domain: validate first, then create, then query. Not too few or too many.

Completeness4/5

Covers the core workflow (validate, submit, query). A tool for cancellation or updating would be ideal but is not strictly necessary for the stated purpose.

Available Tools

3 tools
create_invoiceAInspect

Sign and submit a Nigeria e-invoice to FIRS / NRS MBS — POST /invoice/sign. FIRS signs it server-side and returns the official IRN (Invoice Reference Number), CSID (Cryptographic Stamp Identifier) and QR code to print on the invoice. Bring your own credentials via headers x-firs-api-key AND x-firs-api-secret. The IRN format is InvoiceNumber-ServiceID-YYYYMMDD (e.g. ITW20853450-6997D6BB-20240703): pass irn directly if you already have it, otherwise this server builds it from invoice_number + service_id + issue_date. You send flat fields; the server builds the UBL-mapped JSON and computes VAT (7.5% Nigeria standard rate by default; override per line with vat_rate) into tax_total and legal_monetary_total. Recommended: call validate_invoice first.

ParametersJSON Schema
NameRequiredDescriptionDefault
irnNoOptional ready-made IRN, format InvoiceNumber-ServiceID-YYYYMMDD (e.g. ITW20853450-6997D6BB-20240703). If omitted, built from invoice_number + service_id + issue_date.
itemsYesLine items. Each: name, price (unit price in NGN, tax-EXCLUSIVE), optional quantity (default 1), vat_rate (percent, default 7.5), hsn_code, description, product_category. VAT is computed on top of price*quantity.
issue_dateNoInvoice date YYYY-MM-DD. Defaults to today (UTC).
service_idNoYour FIRS-issued Service ID (the middle segment of the IRN, e.g. 6997D6BB). Used with invoice_number + issue_date to build the IRN. Not needed if you pass irn directly.
business_idYesYour FIRS business_id (UUID) from your NRSMBS Dashboard — identifies the taxpayer entity submitting the invoice.
customer_tinYesBuyer Tax Identification Number (TIN).
supplier_tinYesSeller Tax Identification Number (TIN), e.g. TIN-0099990001.
customer_cityNoOptional buyer city_name.
customer_nameYesBuyer (customer) legal party_name.
supplier_cityNoOptional seller city_name.
supplier_nameYesSeller (supplier) legal party_name as registered with FIRS.
customer_emailNoOptional buyer email.
invoice_numberNoYour own invoice/document number (used to build the IRN, unless you pass irn directly). E.g. INV001.
supplier_emailNoOptional seller email.
customer_streetNoOptional buyer street_name (postal_address).
supplier_streetNoOptional seller street_name (postal_address).
tax_category_idNoOptional FIRS tax_category id for the VAT lines. Default VAT (value-added tax). Use another MBS tax-category code only if the goods fall under a different regime.
invoice_type_codeNoFIRS invoice type code. Default 396 (commercial invoice). See the MBS GetInvoiceTypes list for others.
customer_postal_zoneNoOptional buyer postal_zone (post code).
supplier_postal_zoneNoOptional seller postal_zone (post code).
document_currency_codeNoISO currency of the invoice. Default NGN.
Behavior5/5

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

The description discloses all behavioral traits: server-side signing, IRN generation, VAT computation, credential headers. No contradiction with annotations (readOnlyHint=false, destructiveHint=false).

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

Conciseness4/5

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

The description is informative and front-loaded, but slightly lengthy due to inline details. Every sentence adds value, though it could be more concise by structuring details separately.

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 complex tool with 21 parameters, no output schema, and important logic (IRN generation, VAT), the description covers all essential aspects: purpose, flow, credential handling, and pre-validation recommendation.

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

Parameters5/5

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

Schema coverage is 100%, and the description adds significant value by explaining IRN format construction, VAT defaults, and item structure beyond schema descriptions.

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 verb 'sign and submit', the resource 'Nigeria e-invoice to FIRS / NRS MBS', and the endpoint. It distinguishes from siblings by mentioning validate_invoice first.

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

Usage Guidelines4/5

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

The description explains when to use (to submit a signed e-invoice) and provides a recommendation to call validate_invoice first. It lacks explicit 'when not to use' but overall guidance is good.

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

query_invoiceA
Read-only
Inspect

Look up a signed Nigeria e-invoice by its IRN at FIRS / NRS MBS — GET /invoice/confirm/{irn}. Returns the transmission / delivery status and the IRN/CSID. Safe to call anytime.

ParametersJSON Schema
NameRequiredDescriptionDefault
irnYesThe IRN returned by create_invoice, format InvoiceNumber-ServiceID-YYYYMMDD (e.g. ITW20853450-6997D6BB-20240703).
Behavior4/5

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

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds context by specifying it's a GET endpoint, naming the return values (transmission/delivery status and IRN/CSID), and confirming it's safe to call anytime, which aligns with the 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?

The description is two sentences with no wasted words. It front-loads the purpose and includes key details (endpoint, return values, safety) in a compact form.

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

Completeness4/5

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

For a simple lookup tool with one parameter and no output schema, the description is adequate: it explains the action, the key input, and the return. It could mention potential errors or limitations, but given the low complexity, it is sufficiently complete.

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?

The parameter 'irn' is fully described in the input schema with format and example. The description does not add further meaning beyond what the schema provides, so it meets the baseline for high schema coverage.

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 looks up a signed Nigeria e-invoice by IRN, specifying the endpoint and what it returns. The verb 'Look up' and the resource 'e-invoice by its IRN' are specific, and the sibling tools (create, validate) are distinct actions, so differentiation is clear.

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

Usage Guidelines3/5

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

The description does not explicitly state when to use this tool versus alternatives, but it implies usage after invoice creation by mentioning the IRN returned by create_invoice. 'Safe to call anytime' gives general guidance but no explicit exclusions or alternatives.

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

validate_invoiceA
Read-only
Inspect

Pre-validate a Nigeria e-invoice against FIRS / NRS MBS (Merchant Buyer Solution) BEFORE signing — POST /invoice/validate. Returns pass, or the FIRS error list if the payload is rejected (so you fix it before spending a real submission). Bring your own credentials via headers x-firs-api-key AND x-firs-api-secret (generate them in your NRSMBS Dashboard -> API Integration; your business must be enabled for e-invoicing first). If your Dashboard issued a sandbox base URL, also send header x-firs-base-url. You send flat fields (business_id, supplier/customer party name + TIN, invoice_number, service_id, line items with price); this server builds the UBL-mapped JSON and computes VAT (7.5% default) into tax_total and legal_monetary_total. No fiscal effect — nothing is signed.

ParametersJSON Schema
NameRequiredDescriptionDefault
irnNoOptional ready-made IRN, format InvoiceNumber-ServiceID-YYYYMMDD (e.g. ITW20853450-6997D6BB-20240703). If omitted, built from invoice_number + service_id + issue_date.
itemsYesLine items. Each: name, price (unit price in NGN, tax-EXCLUSIVE), optional quantity (default 1), vat_rate (percent, default 7.5), hsn_code, description, product_category. VAT is computed on top of price*quantity.
issue_dateNoInvoice date YYYY-MM-DD. Defaults to today (UTC).
service_idNoYour FIRS-issued Service ID (the middle segment of the IRN, e.g. 6997D6BB). Used with invoice_number + issue_date to build the IRN. Not needed if you pass irn directly.
business_idYesYour FIRS business_id (UUID) from your NRSMBS Dashboard — identifies the taxpayer entity submitting the invoice.
customer_tinYesBuyer Tax Identification Number (TIN).
supplier_tinYesSeller Tax Identification Number (TIN), e.g. TIN-0099990001.
customer_cityNoOptional buyer city_name.
customer_nameYesBuyer (customer) legal party_name.
supplier_cityNoOptional seller city_name.
supplier_nameYesSeller (supplier) legal party_name as registered with FIRS.
customer_emailNoOptional buyer email.
invoice_numberNoYour own invoice/document number (used to build the IRN, unless you pass irn directly). E.g. INV001.
supplier_emailNoOptional seller email.
customer_streetNoOptional buyer street_name (postal_address).
supplier_streetNoOptional seller street_name (postal_address).
tax_category_idNoOptional FIRS tax_category id for the VAT lines. Default VAT (value-added tax). Use another MBS tax-category code only if the goods fall under a different regime.
invoice_type_codeNoFIRS invoice type code. Default 396 (commercial invoice). See the MBS GetInvoiceTypes list for others.
customer_postal_zoneNoOptional buyer postal_zone (post code).
supplier_postal_zoneNoOptional seller postal_zone (post code).
document_currency_codeNoISO currency of the invoice. Default NGN.
Behavior4/5

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

Annotations already declare readOnlyHint: true; the description reinforces this with 'No fiscal effect — nothing is signed.' It also discloses behavior: returns pass or error list, builds UBL JSON, computes VAT, and requires API keys. This adds valuable context beyond the annotations.

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

Conciseness4/5

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

The description is a single coherent paragraph with no wasted words. It is front-loaded with purpose and covers authentication, parameters, and safety. Could be slightly more structured, but it's efficient and clear.

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 complexity (21 parameters, 6 required), the description thoroughly covers prerequisites (API keys, business enabled), parameter usage, return format, and safety. It is complete for an AI agent to use 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?

Schema coverage is 100% with detailed property descriptions. The description adds extra context, explaining how parameters are used together (e.g., 'You send flat fields; this server builds the UBL-mapped JSON'), and details IRN construction. This enhances understanding beyond the schema.

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 purpose: 'Pre-validate a Nigeria e-invoice against FIRS / NRS MBS BEFORE signing'. It specifies the resource (invoice), action (pre-validate), and endpoint, distinguishing it from sibling tools that are for actual creation or query.

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

Usage Guidelines4/5

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

The description indicates when to use it (before signing, to fix errors) and implies not for actual submission. It mentions it's a pre-check with no fiscal effect. However, it does not explicitly list alternatives like create_invoice for actual submission, but the context is clear.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources