Skip to content
An:des

Connect your Claude / GPT

Your Claude or ChatGPT, connected to An:des

AndesLex is the An:des app: the name of the connector and of your account.

These steps are for Claude. In Your systems and AI, you can explore the available connections for other assistants.

What you need

  • A Claude account on a plan that lets you add custom connectors
  • Your AndesLex account

Add the connector

  1. In Claude, open Settings → Connectors → Add custom connector
  2. Name: AndesLex. URL: https://andeslex.cl/api/mcp
  3. Press Connect, sign in with your AndesLex account and review the consent: it states which program you can read and until what date

Try it

  • «Which programs do I have in AndesLex?»
  • «In the test program, what is missing and who must resolve it?»
  • «What capabilities does the system have?»
  • «Review the screening of the sample supplier.»

What it does and what it does not

  • Claude reads only what your delegation authorizes, and every read is logged in An:des
  • It does not approve or sign. Approvals stay with whoever holds the authority within your organization
  • The delegation has an end date and can be revoked

How An:des governs your AI

  • Investiture: your AI acts only with a delegation in force, granted by whoever holds the authority, with an end date and revocable.
  • Competence: only the programs and services the delegation names; everything else is out of scope.
  • Form: every read and every contribution is logged, with its PoD, and Argos verifies before anything goes out.

This is how An:des works with Érika and with any AI you connect: if the delegation is not current or the action falls outside what it names, the app rejects it; what it does is recorded. Users, credentials, access and credits, each in its own place.

You decide how much it does on its own

  1. Explains: your position, your risks and what is missing
  2. Suggests: the next steps, with their reason
  3. Prepares: drafts that do not go out without your approval
  4. Executes: bounded, low-risk tasks, logged and reversible; never acts

Anything high-risk always goes through whoever holds the authority, and an emergency stop halts it all. An:des communicates only with whoever you authorize, under the rules you approved beforehand. That way, what the AI reads and reports in your case is recorded, with the delegation that authorized it.

Your AI, connectedThree blocks, Claude, ChatGPT and your code, joined to An:des by a bundle of fine lines: the MCP protocol. Over the bundle, three labels: permissions, logging and PoD. A sharp rectangle focuses on An:des.CLAUDECHATGPTYOUR CODEPERMISSIONSLOGGINGPoDAn:desMCP
Your AI, connectedThree blocks, Claude, ChatGPT and your code, joined to An:des by a bundle of fine lines: the MCP protocol. Over the bundle, three labels: permissions, logging and PoD. A sharp rectangle focuses on An:des.CLAUDECHATGPTYOUR CODEPERMISSIONSLOGGINGPoDAn:desMCP
Your AI, connectedThree blocks, Claude, ChatGPT and your code, joined to An:des by a bundle of fine lines: the MCP protocol. Over the bundle, three labels: permissions, logging and PoD. A sharp rectangle focuses on An:des.CLAUDECHATGPTYOUR CODEPERMISSIONSLOGGINGPoDAn:desMCP
Your AI, connectedThree blocks, Claude, ChatGPT and your code, joined to An:des by a bundle of fine lines: the MCP protocol. Over the bundle, three labels: permissions, logging and PoD. A sharp rectangle focuses on An:des.CLAUDECHATGPTYOUR CODEPERMISSIONSLOGGINGPoDAn:desMCP
Your AI, connectedThree blocks, Claude, ChatGPT and your code, joined to An:des by a bundle of fine lines: the MCP protocol. Over the bundle, three labels: permissions, logging and PoD. A sharp rectangle focuses on An:des.CLAUDECHATGPTYOUR CODEAn:desPERMISSIONSLOGGINGPoDMCP

Twelve services, in three governances and one transversal

Existence: read the program’s status and its list screening, with matches and sources. Absence: read the work, with its pending items, and submit a report. Artifact: read a PoD receipt, prepare and track a document batch, and continue its intake, verify each file and request the close. Transversal: list your authorized programs and the system’s capabilities. Every service requires the delegation in force; a read grants no authority and a report does not decide.

Your AI, via MCP: twelve servicesYour AI, whether Claude or your code, connects via MCP with OAuth and a per-case delegation: actions, end date and revocation; ChatGPT comes in through actions. Twelve services in three governances and one transversal: Existence, the program’s status and screening; Absence, Work and reports; Artifact, PoD receipts, document batches and the intake of originals; Transversal, the authorized programs and the capabilities. Argos verifies first, the PoD remains and the answer goes back to your AI, with limits per connection. Measured: Sentinel reads the validity proof of a rule in 4 seconds; an Érika answer with citations, 52.YOUR AIClaude · ChatGPT · your codeOAUTH · DELEGATIONprogram · permissions · until whenG1 EXISTENCEProgram statusScreeningG2 ABSENCEWorkReportsG3 ARTIFACTPoD receiptsPrepare a batchBatch statusPrepare an intakeVerify the intakeClose the intakeTRANSVERSALAuthorized programsCapabilitiesARGOS VERIFIESPoDBACK TO YOUR AILimits: credits · users ·validity · revocableMeasured: a validity change in 4 s ·answer in 52 s
Your AI, via MCP: twelve servicesYour AI, whether Claude or your code, connects via MCP with OAuth and a per-case delegation: actions, end date and revocation; ChatGPT comes in through actions. Twelve services in three governances and one transversal: Existence, the program’s status and screening; Absence, Work and reports; Artifact, PoD receipts, document batches and the intake of originals; Transversal, the authorized programs and the capabilities. Argos verifies first, the PoD remains and the answer goes back to your AI, with limits per connection. Measured: Sentinel reads the validity proof of a rule in 4 seconds; an Érika answer with citations, 52.YOUR AIClaude · ChatGPT · your codeOAUTH · DELEGATIONprogram · permissions · until when · revocableG1 EXISTENCEProgram statusScreeningG2 ABSENCEWorkReportsG3 ARTIFACTPoD receiptsPrepare a batchBatch statusPrepare an intakeVerify the intakeClose the intakeTRANSVERSALAuthorized programsCapabilitiesARGOS VERIFIES FIRSTPoDBACK TO YOUR AILimits per connection: credits · users · validity · revocableMeasured in the app: Sentinel sees a validity change in 4 s ·Érika answer with citations in 52 s
Your AI, via MCP: twelve servicesYour AI, whether Claude or your code, connects via MCP with OAuth and a per-case delegation: actions, end date and revocation; ChatGPT comes in through actions. Twelve services in three governances and one transversal: Existence, the program’s status and screening; Absence, Work and reports; Artifact, PoD receipts, document batches and the intake of originals; Transversal, the authorized programs and the capabilities. Argos verifies first, the PoD remains and the answer goes back to your AI, with limits per connection. Measured: Sentinel reads the validity proof of a rule in 4 seconds; an Érika answer with citations, 52.YOUR AIClaude · ChatGPT · your codeOAUTH · DELEGATIONprogram · permissions · until when · revocableG1 EXISTENCEProgram statusScreeningG2 ABSENCEWorkReportsG3 ARTIFACTPoD receiptsPrepare a batchBatch statusPrepare an intakeVerify the intakeClose the intakeTRANSVERSALAuthorized programsCapabilitiesARGOS VERIFIES FIRSTPoDBACK TO YOUR AILimits per connection: credits · users · validity · revocableMeasured in the app: Sentinel sees a validity change in 4 s · Érika answer with citations in 52 s

Measured in the app on Sep 25, 2026: Sentinel detects in 4 seconds that a rule’s validity no longer matches its source. Érika retrieves an answer with its citations in 52 seconds. You are in the real agent ecosystem: the same connector serves Claude, ChatGPT and your own code.

Before you start

Privacy