Which integrations are available for this server?

lobbyvoices-mcp

Overview Schema Source Related Servers Discussions Admin

Lobby — AI Receptionist Toolkit (MCP server)

MCP Registry

The official MCP server for Lobby — the bilingual AI front desk. It gives any AI agent eight free, no-auth receptionist tools, served remotely over Streamable HTTP. No key, no signup.

https://lobbyvoices.com/api/mcp

The remote endpoint above needs nothing installed — most MCP clients (Claude Code, Cursor, Claude Desktop) can call it directly over HTTP. This repo also ships lobbyvoices-mcp, a tiny stdio bridge (npx/Docker) for clients that only support local stdio servers.

Connect

Claude Code (remote, no install)

claude mcp add --transport http lobbyvoices https://lobbyvoices.com/api/mcp

Cursor · Claude Desktop · any MCP client (remote, no install)

{
  "mcpServers": {
    "lobbyvoices": { "url": "https://lobbyvoices.com/api/mcp" }
  }
}

Stdio-only client — via npx (not published to npm; installs straight from this repo)

{
  "mcpServers": {
    "lobbyvoices": { "command": "npx", "args": ["-y", "github:bodyegypt/lobbyvoices-mcp"] }
  }
}

Stdio-only client — via Docker

docker build -t lobbyvoices-mcp https://github.com/bodyegypt/lobbyvoices-mcp.git

{
  "mcpServers": {
    "lobbyvoices": { "command": "docker", "args": ["run", "-i", "--rm", "lobbyvoices-mcp"] }
  }
}

The bridge does no protocol work itself — it's the maintained mcp-remote package pointed at the production endpoint (see index.js).

Related MCP server: Smallest MCP Server

Tools

Tool	What it does
`write_phone_script`	Writes a business phone script — greeting, voicemail, on-hold, or jingle — in English, Mexican Spanish, or both. Ready to record.
`write_ivr_menu`	Builds a complete IVR / phone-menu script: greeting, numbered options, optional press-9 Spanish switch, operator line.
`generate_elevenlabs_agent_prompt`	Generates a production-grade system prompt for an ElevenLabs conversational agent acting as a phone receptionist.
`calculate_missed_call_cost`	Computes the revenue a business loses to missed calls (monthly + yearly) plus recovery math, break-even days, and ROI.
`simulate_receptionist_call`	Role-play a call against the receptionist call engine — you play the caller, get the transcript, outcome, and automatic EN/ES switch back.
`get_demo_call_number`	A real phone number anyone can call right now to hear the receptionist live, with suggested bilingual scripts.
`should_i_hire_a_receptionist`	Scores a business's phone coverage and returns a verdict — covered, AI front desk, or hybrid — with archetype and leak numbers.
`save_my_receptionist`	Saves a phone script, IVR menu, agent prompt, or simulated call built earlier in the conversation and emails it to the person, with the demo number and a signup link. Requires their explicit consent — only fires with `consent: true`.

Every tool declares an outputSchema and returns structuredContent, so agents get typed JSON instead of text to parse.

Try it with curl

curl -X POST https://lobbyvoices.com/api/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"calculate_missed_call_cost","arguments":{"callsPerWeek":75,"missedRatePct":33,"avgJobValue":380}}}'

Also available as a plain REST API

The same capabilities are exposed as a free, no-key HTTP API — see the developer docs and the OpenAPI spec.

Fair use

No auth required. Per-IP rate limits (AI-backed tools: 2 requests/minute; math and template tools are generous) and hard input caps keep the service healthy. Building something bigger on top? Tell us.

About Lobby

Lobby is an AI front desk for small businesses: it answers every inbound call 24/7, books appointments, captures leads, and speaks English and Mexican Spanish — switching mid-call when the caller does. This MCP server runs on the same production stack.

Available Tools

8 tools

calculate_missed_call_costCalculate what missed calls cost a businessA

Computes the revenue a business loses to missed phone calls (monthly and yearly), plus the recovery math: recoverable revenue, suggested answering plan, break-even days, and ROI multiple.

ParametersJSON Schema

Name	Required	Description
`avgJobValue`	Yes	Average value of one new customer or job, USD.
`callsPerWeek`	Yes	Inbound calls per week.
`missedRatePct`	Yes	Percent of calls missed or sent to voicemail.

Output Schema

ParametersJSON Schema

Name	Required	Description
`inputs`	No
`yearly`	Yes
`monthly`	Yes
`recovery`	Yes

TDQS

A3.9/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses what the tool computes (lost revenue, recovery metrics) and mentions specific outputs (recoverable revenue, suggested plan, break-even days, ROI multiple). This adds value, though assumptions (e.g., constant call volume) are not stated.

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 sentence that packs all key information without redundancy. It could be slightly more structured (e.g., separating lost revenue and recovery math), but it remains efficient and front-loaded.

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?

Given 3 parameters with 100% schema coverage and an output schema, the description is fairly complete. It covers both the primary computation and the additional recovery analysis, leaving only minor gaps (e.g., explicit return format, but output schema presumably covers that).

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?

Schema coverage is 100%, and the description does not add meaning beyond what the schema provides for the three parameters. Baseline of 3 is appropriate since the schema already documents each parameter.

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 computes revenue lost to missed calls (monthly/yearly) and recovery math, which is a specific verb+resource. It distinguishes itself from siblings that focus on prompts, demos, hiring decisions, or scripting.

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?

No explicit guidance on when to use this tool versus alternatives like 'should_i_hire_a_receptionist'. Usage is implied from the title and description, but no exclusions or context for selection are provided.

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

generate_elevenlabs_agent_promptGenerate an ElevenLabs agent system promptB

Generates a production-grade system prompt for an ElevenLabs conversational agent acting as a business phone receptionist: identity, job, voice style, booking flow, guardrails, and escalation rules.

ParametersJSON Schema

Name	Required	Description
`biz`	Yes	Business name (required).
`tone`	No	Personality, e.g. warm, formal, upbeat.
`hours`	No	Business hours in plain words.
`tasks`	No	What the agent should do, e.g. book, faqs, leads.
`spanish`	No	Whether the agent should also handle Spanish callers.
`industry`	No	Industry, e.g. plumbing, hvac, dental, salon, law, restaurant.
`agentName`	No	Name the agent should use for itself.

Output Schema

ParametersJSON Schema

Name	Required	Description
`prompt`	Yes	The complete system prompt, ready to paste into ElevenLabs.
`sections`	No	The prompt broken into tagged sections.

TDQS

B3.4/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of disclosing behavior. It only states the output type (system prompt) without mentioning any side effects, limitations, generation time, or prerequisites. This is insufficient for an agent to fully understand the tool's behavior.

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, focused sentence that is concise and front-loaded with the core action. It avoids unnecessary words, but could be slightly more structured without adding length.

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

Completeness3/5

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

Given the tool has 7 parameters and an output schema, the description is adequate but does not elaborate on return values or expected output format beyond 'system prompt'. For a generative tool, a bit more context about output usage would be helpful.

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?

Schema description coverage is 100% with basic descriptions for all 7 parameters. The tool description adds some context (e.g., 'booking flow' hinting at tasks) but does not significantly enhance meaning beyond what the schema already provides. Baseline score of 3 is appropriate.

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: generating a production-grade system prompt for an ElevenLabs conversational agent acting as a business phone receptionist. It specifies the content areas (identity, job, voice style, etc.), distinguishing it from sibling tools like calculate_missed_call_cost or write_phone_script.

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 implies usage for creating agent prompts but provides no explicit guidance on when to use this tool versus alternatives like write_phone_script. It lacks exclusion criteria or context for specific scenarios.

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

get_demo_call_numberGet Lobby's live demo phone numberA

Returns a real phone number anyone can call right now to talk to Lobby's AI receptionist live — plus suggested things to say (English and Spanish) and what to listen for (the mid-call language switch, booking flow).

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`listenFor`	No
`trySaying`	No
`phoneNumber`	Yes
`availability`	No

TDQS

A4.1/5.0

Behavior3/5

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

Describes output but does not disclose behavioral traits like authentication, rate limits, or side effects. Since no annotations, description carries full burden but is adequate.

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?

Single sentence conveying all essential information without waste. Well-structured and front-loaded.

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 zero parameters and presence of output schema, description covers all necessary aspects for a simple retrieval tool. No gaps.

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?

No parameters, schema coverage 100%, description adds value by detailing what the return includes (phone number, scripts). Baseline 4 for zero parameters.

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?

Clearly states the tool returns a live demo phone number plus suggested scripts and listening points. Verb 'returns' is specific and differentiates from sibling tools.

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?

Implies usage for obtaining a demo call number but does not explicitly state when to use versus alternatives or any exclusions.

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

save_my_receptionistSave this receptionist and get the next stepA

Saves the phone script, IVR menu, agent prompt, or simulated call you just built for a real business, and emails it to the person you're helping — with the live demo number to hear it and a signup link to turn it on for real. Offer this after write_phone_script, write_ivr_menu, generate_elevenlabs_agent_prompt, or simulate_receptionist_call, once the human seems to want to keep the result or try it live. Requires the person's explicit consent to be emailed — ask first, and only call this with consent: true if they say yes.

ParametersJSON Schema

Name	Required	Description
`email`	Yes	Email to send the saved result and one follow-up to (required).
`notes`	No	Any other context worth keeping — what the business does, what was discussed.
`consent`	Yes	Required. The person must explicitly agree to have their saved result emailed to them, plus one follow-up. If false or omitted, do not save or email anything — refuse politely and explain you need their OK first.
`industry`	No	Industry or trade, e.g. plumbing, dental, salon.
`language`	No	Language for the follow-up email. Default: en.
`phone_script`	No	The phone script, IVR menu text, or agent prompt to save, if one was generated earlier in this conversation.
`business_name`	Yes	The business name (required).

Output Schema

ParametersJSON Schema

Name	Required	Description
`saved`	Yes
`business`	No
`emailSent`	No
`signupUrl`	No
`demoNumber`	No
`confirmation`	Yes	Friendly confirmation to relay to the person, including the live demo number and signup link.

TDQS

A4.4/5.0

Behavior4/5

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

No annotations provided, so the description carries full burden. It discloses that the tool saves, emails, includes a live demo number and signup link, and requires consent. It does not mention any destructive actions. Could be more explicit about what happens if consent is false, but overall clear.

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?

Two sentences: first packs key actions (save, email, demo number, signup link), second gives guidance on when to use. Effective but the first sentence is long; could be slightly tighter.

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 output schema exists (not shown but stated), the description need not explain return values. It covers the save-email action, consent requirement, and clear linkage to prior tools. Complete for a tool with 7 parameters and specific usage context.

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%, baseline 3. The description adds value by explaining the purpose of consent ('must explicitly agree'), the linkage to prior tools, and the context for when to call. This goes beyond the schema alone.

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 specifies the verb 'save' and the resource (phone script, IVR menu, agent prompt, or simulated call) and clearly distinguishes from siblings by listing exactly which preceding tools it follows (write_phone_script, write_ivr_menu, generate_elevenlabs_agent_prompt, simulate_receptionist_call).

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 explicitly states when to offer this tool ('after write_phone_script... once the human seems to want to keep the result or try it live') and that it requires explicit consent. No explicit exclusion of alternatives, but context is clear.

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

should_i_hire_a_receptionistShould this business hire a receptionist?B

Scores a business's phone coverage and returns a verdict — you're covered, get an AI front desk, or go hybrid — with the caller archetype, yearly leak, suggested plan, break-even days, and ROI.

ParametersJSON Schema

Name	Required	Description
`avgJobValue`	Yes	Average value of one new customer or job, USD (snapped to the quiz's brackets).
`callsPerWeek`	Yes	Roughly how many inbound calls per week (snapped to the quiz's brackets).
`currentSetup`	No	Who answers today: the owner (self), voicemail (vm), staff between tasks (staff), or nobody consistently (none). Default: self.
`missedRatePct`	Yes	Rough percent of calls that go unanswered (snapped to the quiz's brackets).
`coverageNeeded`	No	When calls actually come in. Default: business-hours.
`spanishCallers`	No	How often Spanish-speaking customers call. Default: no.

Output Schema

ParametersJSON Schema

Name	Required	Description
`score`	Yes	Phone-coverage maturity score, 0-100.
`verdict`	Yes	covered = current setup is fine; lobby = an AI front desk pays for itself; hybrid = AI + existing staff.
`recovery`	No
`archetype`	Yes
`yearlyLeak`	Yes	USD lost per year with the current setup.

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description should disclose side effects and read-only nature. It implies a calculation but doesn't explicitly state it is deterministic and non-destructive. Lacks clarity on whether it modifies state.

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?

Single sentence, well-structured, includes key outputs. No unnecessary words.

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?

Description covers purpose, verdict types, and return fields. With output schema present, it is fairly complete. Could mention it's a scoring/calculation tool but overall sufficient.

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?

Schema coverage is 100%, so baseline 3. Description adds no parameter context beyond what schema provides, but schema is complete. No extra semantic guidance on parameter importance or relationships.

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 clearly states the tool scores phone coverage and returns a verdict with metrics, using specific verbs. However, it does not differentiate from sibling tools like calculate_missed_call_cost or simulate_receptionist_call.

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

Usage Guidelines2/5

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

No guidance on when to use this tool vs alternatives such as calculate_missed_call_cost or simulate_receptionist_call. Missing context on prerequisites or scenarios.

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

simulate_receptionist_callSimulate a call with the Lobby receptionistA

Role-play a phone call with Lobby's receptionist call engine — the same pipeline behind the product demo: greeting, booking flow, lead capture, and automatic English/Spanish detection (live calls add a full AI brain on top). You play the caller: pass each thing the caller says, get the full transcript and outcome back. Free, text-only, max 6 caller lines.

ParametersJSON Schema

Name	Required	Description	Default
`business`	No	Business name the receptionist answers for. Default: Lobby Demo Services.
`callerSays`	Yes	The caller's lines, in order. Try Spanish to hear the language switch — e.g. ['Hola, necesito una cita para mañana.']

Output Schema

ParametersJSON Schema

Name	Required	Description
`booked`	No
`outcome`	Yes
`language`	Yes	Language the receptionist detected and answered in.
`hearItLive`	No	Phone number to call to experience the same receptionist with a real voice.
`transcript`	Yes
`leadCaptured`	No

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses the pipeline stages, language detection capability, and the fact that it's the same pipeline as the demo (but without the 'full AI brain'). It also notes it's free and text-only, which are key behavioral traits for an AI agent.

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 extremely concise: two sentences that effectively front-load the purpose and then provide usage instructions. Every sentence adds value with no redundancy or fluff.

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?

Despite moderate complexity, the description covers input, behavior, constraints, and hints at output. Since an output schema exists, the lack of explicit return value details is acceptable. The description is complete for an AI agent to understand and invoke the tool correctly.

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. The description adds value by providing an example (Spanish language switch) and explaining that callerSays is the caller's lines in order. This helps the agent understand how to format input beyond the schema's description.

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: role-playing a phone call with Lobby's receptionist call engine. It lists key features (greeting, booking, lead capture, language detection) and explicitly distinguishes from sibling tools like calculate_missed_call_cost, making its purpose unmistakable.

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 provides clear usage guidance: the user plays the caller, passes each line, and receives transcript and outcome. It specifies constraints (free, text-only, max 6 lines) and hints at language switching. While it doesn't explicitly contrast with siblings, the context makes it obvious when to use this tool.

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

write_ivr_menuWrite an IVR phone-menu scriptA

Builds a complete IVR (phone menu / auto-attendant) script for a business: greeting, numbered options, optional Spanish-language switch, and the operator line. English, Spanish, or bilingual.

ParametersJSON Schema

Name	Required	Description
`options`	No	Menu options in order (press 1, press 2, …). Defaults to the industry's standard four.
`business`	Yes	Business name (required).
`greeting`	No	Custom opening greeting. Default: 'Thank you for calling {business}.'
`industry`	No	Pick the closest industry; supplies sensible default menu options.
`language`	No	Menu language. 'both' adds a press-nine Spanish switch. Default: en.

Output Schema

ParametersJSON Schema

Name	Required	Description
`lines`	Yes
`recordAt`	No	URL of the free web tool that records this menu in a real AI voice.
`scriptText`	Yes	The full menu as one recordable script.

TDQS

A3.8/5.0

Behavior2/5

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

With no annotations, the description carries the full burden. It states the tool 'Builds' a script, suggesting a creation action, but lacks details on side effects, idempotency, required permissions, or whether it modifies existing resources. Behavioral traits beyond the obvious script generation are absent.

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: the first states the core action and components, the second lists language variants. It is front-loaded with no redundant words, earning a top conciseness score.

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?

Given 5 parameters, 100% schema coverage, and an output schema, the description covers the main outcome and parameter semantics well. It could be improved by mentioning that the output is a formatted script or that options are limited to 6 (already in schema), but overall it provides sufficient context for a complex tool.

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 baseline is 3. The description adds value by explaining defaults ('industry's standard four' for options, 'Thank you for calling {business}' for greeting) and the 'both' language option with the press-nine switch. This context helps agents choose parameter values wisely.

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 'Builds a complete IVR script' with specific components: greeting, numbered options, optional Spanish switch, and operator line. This distinguishes it well from the sibling 'write_phone_script', which likely covers a broader set of phone scripts.

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 implies use for building an IVR menu with industry defaults but does not explicitly state when to use this tool versus alternatives like 'write_phone_script' or 'simulate_receptionist_call'. There is no guidance on when not to use it.

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

write_phone_scriptWrite a business phone scriptB

Writes a professional phone script for a business — greeting, voicemail message, on-hold message, or jingle lines — in English, Mexican Spanish, or both. Returns ready-to-record text.

ParametersJSON Schema

Name	Required	Description
`mode`	No	What kind of script to write. Default: greeting.
`vibe`	No	Tone of voice. Default: warm.
`extra`	No	Optional details to mention: hours, offers, callback promise.
`langs`	No	Languages to write. Default: both.
`trade`	No	Industry or trade, e.g. plumbing, dental clinic.
`business`	Yes	Business name (required).

Output Schema

ParametersJSON Schema

Name	Required	Description
`scripts`	Yes

TDQS

B3.2/5.0

Behavior2/5

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

With no annotations, the description carries full burden. It mentions returns 'ready-to-record text' but lacks details on side effects, permissions, or limitations.

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?

Single sentence, front-loaded with purpose, no wasted words. Could be slightly more structured but efficient.

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

Completeness3/5

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

Covers basic functionality and output expectation, but given presence of output schema and 6 params, more behavioral context would be beneficial.

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?

Schema coverage is 100%, so baseline 3. The description adds context like script types and languages, but does not significantly enhance parameter 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 it writes a professional phone script and lists specific script types (greeting, voicemail, etc.), distinguishing it from sibling tools like write_ivr_menu.

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

Usage Guidelines2/5

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

No guidance on when to use this tool vs alternatives or any prerequisites. The description only states what it does.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

8 tool updatesv1.3.1Jul 3, 2026
- First observedcalculate_missed_call_cost
- First observedgenerate_elevenlabs_agent_prompt
- First observedget_demo_call_number
- First observedsave_my_receptionist
- First observedshould_i_hire_a_receptionist
- First observedsimulate_receptionist_call
- First observedwrite_ivr_menu
- First observedwrite_phone_script

Deploy Server

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

TDQS

A3.8/5.0

Scored 2026-07-05 05:10 across 8 tools

Disambiguation4/5

Tools are mostly distinct with clear purposes, though write_phone_script and write_ivr_menu both involve script writing, and generate_elevenlabs_agent_prompt overlaps slightly with writing textual prompts. However, each targets a specific aspect of the receptionist workflow.

Naming Consistency4/5

Most tools follow a verb_noun pattern (calculate_, generate_, etc.), but 'should_i_hire_a_receptionist' breaks the pattern with a full question, and 'save_my_receptionist' uses an informal style. Overall consistent with minor deviations.

Tool Count5/5

8 tools is well-scoped for the domain of AI phone receptionists, covering analysis, creation, testing, and saving without being overwhelming or sparse.

Completeness4/5

The set covers the full lifecycle: decision support, script writing, prompt generation, simulation, and saving. Minor gaps like a tool to list existing saved scripts or edit them are absent, but core workflows are complete.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

supportsheep
io.github.pooriaarab
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Customer Support Content Management Systems Marketing
1
omnidim-mcp-serverOAuth
io.github.Omnidim
Official MCP server for OmniDimension. Drive voice agents, dispatch calls, and run bulk campaigns.
Communication Speech Processing
27
LovableOAuth
dev.lovable
Official MCP server for Lovable, the AI-powered full-stack app builder.
Developer Tools AI & Machine Learning
24
UnifAPIOAuth
com.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
Open Data Search AI & Machine Learning
2

Related MCP Servers

bubblyphone-agents
Communication Agent Orchestration Customer Support
JobXDubai
A
license
A
quality
D
maintenance
MCP server for BubblyPhone that lets AI assistants make real phone calls, manage AI voice agents, buy phone numbers in 30+ countries, and track billing. Supports 20 tools for full telephony control.
Updated 5 months ago (2026-04-04 08:47 UTC)
20
5 npm
1
MIT
Smallest MCP Serverofficial
AI & Machine Learning Communication
smallest-inc
A
license
B
quality
A
maintenance
MCP server for the Smallest AI platform that enables managing AI voice agents, debugging calls, and viewing analytics directly from your IDE.
Updated a month ago (2026-08-06 07:43 UTC)
83
52 npm
1
MIT
Arc & Ledger Tax Tools MCP
Finance Legal & Compliance
Bgenc48
F
license
Not graded
quality
B
maintenance
A public, no-auth remote MCP server that exposes Arc & Ledger's free tax calculators and intake funnel as tools inside AI assistants. Provides tools for IRS notice explanation, FBAR/FATCA, LLC vs S-Corp comparison, quarterly tax estimates, and more.
Updated 2 months ago (2026-07-31 01:31 UTC)
-
GoHighLevel MCP Starter
CRM Calendar Management Customer Data Platforms
rockurbusinesscs-ship-it
A
license
A
quality
C
maintenance
MCP server that lets you talk to your GoHighLevel sub-account in plain English, offering six tools to search contacts, list calendars, check free slots, and book appointments with dry-run safety and explicit error messages.
Updated a month ago (2026-08-04 01:45 UTC)
6
MIT

Lobby — AI Receptionist Toolkit (MCP server)

Connect

Tools

Try it with curl

Also available as a plain REST API

Fair use

About Lobby

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Smallest MCP Serverofficial