Skip to main content
Glama
Yasmine-Works

VoIPSense Maroc MCP Server

by Yasmine-Works
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Inject leads in bulk (auto-chunked by 500)

inject_leads_batch
Idempotent

Bulk-inject leads into VoIPSense lists or campaigns, creating/reusing lists, attaching campaigns, and enrolling agents. Idempotent by phone number per list for safe resends.

Instructions

POST /v1/leads/batch (permission callcenter:write). End-to-end provisioning in one call: create/reuse a list, attach it to a campaign (create it if needed), enroll agents, and inject leads. More than 500 leads are automatically split into batches of 500 and the totals are aggregated. Idempotent by phone number per list: safe to resend the full file every cycle. Without any campaign field the leads go to a plain list ("Mes listes" mode).

Input Schema

NameRequiredDescriptionDefault
leadsYesLeads to inject. Any size; sent in batches of 500.
agentsNoExplicit agents to enroll on the campaign: extension number, email or user id (e.g. ["111201","sara@client.ma"]). If none is valid → 400 and nothing is written.
listIdNoTarget list: UUID or the list number shown in the console (e.g. 101). Use listId OR listName.
listNameNoTarget list by exact name. Combine with createList=true to create it if missing.
campaignIdNoAttach the list to an existing campaign by id.
createListNoCreate the list named listName if it does not exist.
dialMethodNoDial mode for a newly created campaign. Default PREVIEW. MANUAL serves no leads; PROGRESSIVE/PREDICTIVE auto-dial.
campaignNameNoAttach the list to a campaign by name. Combine with createCampaign=true to create it.
outboundLineNoWith createList: exact name or id of an active line (trunk) used for every call from this list. Always overrides the campaign line. 400 if unknown/inactive.
createCampaignNoCreate campaignName if missing (OUTBOUND / PREVIEW / ACTIVE: the console serves leads to agents automatically).
updateIfExistsNoUpdate fields of a contact already in the list instead of ignoring it (status/attempts/history are never touched).
assignAllAgentsNoEnroll all active agents of the organization. Ignored if agents is provided.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Beyond annotations, the description discloses the required permission (callcenter:write), automatic chunking above 500 leads with aggregated totals, idempotency keyed by phone number per list, safe resend behavior, and the plain-list fallback when no campaign fields are supplied. These are substantive behavioral facts that materially affect invocation.

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 front-loaded with the endpoint and permission, followed by side effects, chunking, idempotency, and the fallback mode. Every sentence carries operational meaning; nothing is redundant or buried.

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 complex 12-parameter write tool with rich schema descriptions and meaningful annotations, the definition covers permissions, side effects, chunking, idempotency, and mode selection well. It stops short of describing return payload shape or partial-failure behavior, which are not covered by an output schema.

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%, so the baseline is 3, but the description adds cross-parameter meaning: sending no campaign fields routes leads to a plain list in 'Mes listes' mode, and the leads array is automatically chunked at 500. This complements the per-field schema descriptions rather than repeating them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('inject leads', POST /v1/leads/batch) and enumerates the orchestration it performs: create/reuse a list, attach to a campaign, enroll agents. It does not explicitly name the singular sibling inject_lead, but the batch scope is clear from the name, title, and chunking behavior.

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?

It gives clear usage context: use for end-to-end bulk provisioning, safe to resend the full file each cycle thanks to idempotency, and leads go to a plain list when no campaign field is provided. It stops short of explicitly naming alternatives such as inject_lead for a single lead or list_lists for discovery.

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

Deploy Server

Other Tools