Conecto

Connect a system

connect_add

Connect one of the company's own systems (an ERP, a ticketing tool, any REST API): its https base address, its credential and the calls the agent may make. Called without secret, it answers with a link for the owner, who sees the address and the calls and types the credential on a Conecto page, so it never passes through the chat (from_a_terminal does the same from a terminal); account.credential_added says when it is connected. The credential is kept encrypted and never shown again. A system behind the company's firewall goes through one of its bridges instead: give bridge and system (connect_list shows the bridges and the systems each serves) in place of base_url and a credential, which the bridge adds inside the network. On accounts with an owner, writes (POST, PUT, PATCH, DELETE) and changing the allowed calls wait for the owner's approval by default, which shows the exact request. Free. Free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "allow": "<allow>"
    },
    "name": "connect_add"
  }
}

Input Schema

Name	Required	Description	Default
`auth`	No	bearer (Authorization: Bearer <secret>), header (the secret in `header`), basic (secret is "user:password") or none.	bearer
`name`	Yes	Lowercase letters, digits and dashes, like "netsuite" or "zendesk".
`allow`	Yes	The calls it may make: a method and a path pattern each, like "GET /v1/customers" or "POST /v1/tickets". matches anything.
`bridge`	No	For a system behind the firewall: the bridge it goes through.
`header`	No	For auth header, like X-API-Key.
`secret`	No	The credential: a token, the header's key, or "user:password" for basic. Leave it out to get the link instead.
`system`	No	With bridge: the system's name in the bridge's config, like "sap".
`base_url`	No
`description`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

addedInput schema / properties / secret / description

Added value: +"The credential: a token, the header's key, or \"user:password\" for basic. Leave it out to get the link instead."

First observedOct 28, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations: the secret never transits the chat, an owner link is returned, account.credential_added signals connection, the credential is stored encrypted and never shown again, and writes/changed allow-lists wait for owner approval showing the exact request. These are exactly the non-obvious traits an agent needs before calling.

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

Conciseness3/5

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

Content is dense and front-loaded, but it is delivered as one long paragraph and ends with a duplicated 'Free. Free.', which is a clear editing defect. Most sentences earn their place; the redundancy and lack of structure cost it.

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?

With 9 parameters, no output schema and 78% schema coverage, the description supplies the missing operational picture: what is returned when secret is omitted, how approval gates changes, and how the bridge path differs. Remaining gaps are failure handling and idempotency behaviour (e.g. what a second call with the same name does), which annotations flag as non-idempotent.

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 78%, so the schema already documents most parameters (baseline 3). The description adds real meaning the schema cannot: bridge+system substitute for base_url and the credential together, and omitting secret switches the call to link-return mode rather than failing.

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?

States a specific verb and resource (connect one of the company's own systems — ERP, ticketing tool, any REST API) and immediately scopes it to base address, credential and allowed calls. Names the sibling alternatives (from_a_terminal, connect_list) so it is distinguishable without opening other schemas.

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?

Gives explicit conditional paths: omit secret to get an owner link, or pass bridge+system instead of base_url+credential for firewalled systems. Also states the owner-approval condition for writes. It does not say when to prefer connect_preview or connect_set_rules, so it is not fully exhaustive, but the main decision points are covered.

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

All Conecto tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?