Colombia Invoices (DIAN factura electronica via Matias API)
Server Details
Colombia DIAN factura electronica: AI agents issue and query e-invoices, stateless BYO.
- 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.
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.
Tool Definition Quality
Average 4.3/5 across 2 of 2 tools scored.
The two tools have completely distinct purposes: one creates invoices, one queries existing invoices. There is no overlap or ambiguity.
Both tools follow a consistent verb_noun pattern (create_invoice, query_invoice) with clear, predictable naming.
Only 2 tools for a domain that typically requires more (e.g., list, cancel). While focused, the count is borderline low for 'Colombia Invoices' scope.
Missing essential CRUD operations like listing, updating, or canceling invoices. This will cause agent failures for common tasks beyond creation and status lookup.
Available Tools
2 toolscreate_invoiceAInspect
Issue a Colombia electronic invoice (factura de venta / factura electrónica, DIAN UBL 2.1) through Matias API, which digitally signs it and transmits it straight to the DIAN (no Proveedor Tecnológico middleman) from YOUR OWN Matias account — this server only forwards the call and never holds your certificate. It wraps POST /invoice. Amounts are in Colombian pesos (COP, integer convention) and unit prices are TAX-EXCLUSIVE (valor neto, before IVA). IVA (VAT) rate per line: 19 (standard), 5 (reduced), or 0 (exento/excluido); the server liquidates the IVA locally (line net * rate/100) and builds the UBL totals. You must pass your DIAN resolution_number (from the resolución de facturación DIAN issued to your account) and the buyer. On success you get back the DIAN cufe (Código Único de Facturación Electrónica) and the acceptance state. Set x-matias-env=sandbox (default) to build/transmit in the pruebas environment with NO fiscal effect. Required credential header (set once in your MCP client, per-request, never stored): x-matias-token (your Matias bearer token — a JWT access_token from POST /auth/login, or a long-lived Personal Access Token from POST /auth/token). Optional x-matias-env: sandbox (default = pruebas, no fiscal effect) | production (real DIAN fiscal effect). Optional x-matias-base overrides the production base URL Matias assigns on contract. Optional owner-policy headers x-agentpay-max-amount / x-agentpay-approval-above / x-agentpay-allowed-tools.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | Line items. Each: { descripcion, cantidad, precioUnitario (COP integer, TAX-EXCLUSIVE / valor neto), iva? (19|5|0, default 19), codigo?, unidadMedida? (default 70=Unidad) }. | |
| notes | No | Optional free-text note printed on the invoice. | |
| number | No | Sequential invoice number within the resolución range, e.g. 990000001. Optional — omit to let Matias auto-increment (it exposes POST /auto-increment/invoices for that). | |
| prefix | No | Invoice prefix authorized in your resolución, e.g. "SETP" or "FE". Optional if your resolución has no prefix. | |
| customer | Yes | Buyer / adquiriente. For a business use its NIT; for a final consumer you may use the DIAN generic consumer NIT 222222222222 with identity_document_id=6. | |
| send_email | No | true = Matias emails the buyer the invoice. Default false. | |
| type_document_id | No | DIAN document type id in Matias. Default 1 (Factura de Venta Nacional). Override only to match a different type in your Matias document catalog. | |
| operation_type_id | No | DIAN operation type id (tipo de operación). Default 10 (Estándar). | |
| resolution_number | Yes | Your DIAN invoicing resolution number (número de resolución de facturación, issued by the DIAN to your account/prefix). REQUIRED — DIAN rejects an invoice whose number is outside an authorized resolución. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description provides extensive behavioral details beyond annotations: digital signing, direct transmission to DIAN no middleman, server never holds certificate, amounts in COP integer (tax-exclusive), IVA rates, return of cufe and acceptance state. No contradiction with annotations (readOnlyHint=false, idempotentHint=false).
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 packed with necessary details and is well-structured, starting with the main purpose then parameter details and headers. It is slightly verbose with header explanations, but given the complexity of the API, it remains clear and front-loaded.
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 no output schema, the description mentions success returns (cufe and acceptance state). It covers all required parameters, optional parameters, environment headers, and authentication. It could mention error cases, but overall it is sufficiently complete for a complex 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?
All 9 parameters are already described in the schema (100% coverage), but the description adds valuable context such as the meaning of IVA rates (19 standard, 5 reduced, 0 exento), that unit prices are tax-exclusive (valor neto), and the purpose of resolution_number. This enriches understanding beyond the schema.
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 issues a Colombia electronic invoice (factura de venta / factura electrónica, DIAN UBL 2.1) through Matias API, distinguishing it from the sibling query_invoice which queries invoices.
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 explains when to use (e.g., to issue a DIAN invoice) and provides contextual guidance such as required headers, environment selection (sandbox vs production), and critical parameters like resolution_number. It does not explicitly state when not to use, but the sibling tool name implies querying.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_invoiceARead-onlyIdempotentInspect
Look up a previously-issued Colombia document by its uuid (the Matias document UUID returned by create_invoice) to read its DIAN state — wraps GET /documents/{uuid}. Returns the document metadata Matias holds: uuid, cufe (Código Único de Facturación Electrónica), state (the DIAN acceptance state), number, dian_message and created_at. Safe to call anytime; read-only. Required credential header (set once in your MCP client, per-request, never stored): x-matias-token (your Matias bearer token — a JWT access_token from POST /auth/login, or a long-lived Personal Access Token from POST /auth/token). Optional x-matias-env: sandbox (default = pruebas, no fiscal effect) | production (real DIAN fiscal effect). Optional x-matias-base overrides the production base URL Matias assigns on contract. Optional owner-policy headers x-agentpay-max-amount / x-agentpay-approval-above / x-agentpay-allowed-tools.
| Name | Required | Description | Default |
|---|---|---|---|
| uuid | Yes | The Matias document UUID returned by create_invoice (identifies the stored factura electrónica). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive. Description adds details about GET endpoint, return fields, and authentication headers, providing context beyond annotations. No contradiction.
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?
Description front-loads purpose but includes verbose header details that could be separate. While structured, it is longer than necessary for a simple 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?
Covers tool purpose, return fields, authentication, and optional headers. Despite no output schema, the listed return values and safety assurances make it complete for agent selection and 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?
Only parameter 'uuid' has clear schema description. With 100% schema coverage, description repeats the parameter's role but adds no new semantics beyond confirming it comes from create_invoice.
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 clearly states 'Look up a previously-issued Colombia document by its uuid to read its DIAN state', specifying verb, resource, and action. It distinguishes from sibling 'create_invoice' by focusing on querying existing documents.
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?
Explicitly says 'Safe to call anytime; read-only' and implies usage after creating an invoice. With only one sibling, distinction is clear, but could be more explicit about when not to use (e.g., for new documents).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!