Which integrations are available for this server?

Enables secure purchase of recommended gifts through Shopify checkout via the picks URL.

How do I use Present Agent MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Present Agent MCP Find a birthday gift for my best friend under $60" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Present Agent MCP

by GuillaumeRacine

Overview Schema Source Related Servers Score Discussions Admin

TypeScript

Remote

Present Agent MCP

Find 5 explainable, personalized gift recommendations from inside any MCP client — Claude Code, Codex, Cursor, and more.

Current status and split guidance: docs/STATUS.md.

Present Agent is a gifting engine that reasons about the relationship, occasion, and the signal a gift sends — not just product search. This package is the public, hosted MCP server: it calls the live Present Agent API at presentagent.vip, so you need no local product catalog, no Shopify credentials, and no model-provider API keys to get value.

🎁 5 curated picks, each with a plain-language reason it fits
🔌 Works in any MCP-capable client over stdio
🔒 Hosted by default — zero secrets to configure
🌐 Every result includes a shareable web URL you can open or continue in the browser

Full docs & client catalog: https://presentagent.vip/mcp

Quickstart

Claude Code

claude mcp add present-agent --transport stdio --scope user \
  -e PRESENT_AGENT_CLIENT=claude-code \
  -- npx -y present-agent-mcp

Then ask Claude, in any project:

Find a gift for my sister's birthday under $100. She just got into pottery.

Codex

One command writes the config to ~/.codex/config.toml:

npx -y present-agent-mcp setup codex

Use --dry-run to preview without writing, or --local-context to enable opt-in local context (see Local context mode). Restart Codex, then ask for a gift.

Any other MCP client (generic stdio config)

{
  "mcpServers": {
    "present-agent": {
      "command": "npx",
      "args": ["-y", "present-agent-mcp"],
      "env": { "PRESENT_AGENT_CLIENT": "custom" }
    }
  }
}

Requirements: Node.js ≥ 18 and network access to https://presentagent.vip. The first run downloads the package via npx; subsequent runs are cached.

Related MCP server: NeuronSearchLab

Tools

`present_find_gift`

Find 5 personalized gifts through the hosted Present Agent API. Only recipient is required — every other field sharpens the picks but is optional.

Parameter	Type	Description
`recipient`	string · required	Name or short description of who the gift is for.
`relationship`	string	partner, parent, sibling, friend, colleague, client, etc.
`occasion`	string	birthday, anniversary, thank-you, housewarming, onboarding, holiday…
`budget`	string	Free-form: `"$50-100"`, `"under $75"`, `"$150 CAD"`. Prices are CAD.
`interests`	string	Comma-separated interests, hobbies, brands, or taste signals.
`preferences`	string	Known likes, style, taste, or profile clues.
`constraints`	string	Hard rules: avoid categories, delivery deadline, allergies, space, values.
`needs`	string	Functional needs or outcomes the gift should support.
`giver_context`	string	What you (the host AI) know about the giver: budget norms, taste, taboos, prior gifts. Leave empty if unknown — never fabricate.
`recipient_context`	string	What you know about the recipient beyond name/relation/occasion: life events, prior gift outcomes, recent notes. Leave empty if unknown — never fabricate.
`useAgentContext`	boolean	Opt in to local context search. Also requires `PRESENT_ENABLE_LOCAL_AGENT_CONTEXT=1`. Default `false`.

Returns (JSON text):

{
  "mode": "hosted",
  "apiBase": "https://presentagent.vip",
  "sessionId": "51bd7b67-…",
  "picksUrl": "https://presentagent.vip/picks/51bd7b67-…",
  "contextSignals": { "hosted": { "sources": ["explicit input"] } },
  "recommendations": [
    {
      "slot": "top_pick",
      "name": "White — Sage Valley Pottery Pie Dish",
      "brand": "PRINTFRESH",
      "price": 60,
      "matchScore": 0.5,
      "whyThisFits": "Combines her love of pottery with practical kitchen artistry…",
      "giftAngle": "Present it as functional art she'll use regularly."
    }
  ]
}

picksUrl is a real, shareable page — open it, send it, or continue refining in the browser.

`present_beta_start`

Zero-argument tool that returns the fastest onboarding instructions, a live web fallback (/gift/new), and the local-context opt-in hint. Useful as a first call to orient a fresh agent.

How to get the best picks

The engine reasons from context. The more specific, true signal you give it, the better the 5 picks — but don't invent detail.

Name a concrete interest or recent change ("just got into pottery", "started trail running"). Specifics beat adjectives.
State the relationship and occasion — they change what a gift signals.
Put genuine hard limits in constraints ("no alcohol", "ships to Canada by Dec 20", "nut allergy"). Constraints are respected before scoring.
Pass through real memory in giver_context / recipient_context when your host AI already knows it.

Don't

Fabricate interests or budgets to "fill the form" — empty is better than wrong; the model treats blanks honestly.
Expect it to read minds: "something nice" with no other signal yields generic picks.
Use it to search a specific SKU — it recommends what to give, it isn't a product-lookup tool.

Good call:

present_find_gift({ recipient: "my dad", relationship: "parent", occasion: "birthday", budget: "$80-120", interests: "gardening, espresso, jazz vinyl", constraints: "no clothing, he's hard to surprise" })

What's feasible (and what isn't)

✅ Feasible	❌ Not in this MCP
5 explainable gift picks for a person + occasion	Completing a purchase / checkout (happens on the web, link provided)
Budget, hard constraints, and taste honored	Real-time inventory or per-item shipping quotes (confirmed at checkout)
A shareable `picksUrl` for every result	Editing a saved recipient profile or wishlist (web/app feature)
Optional, opt-in local context hints	Reading your full local files (only sanitized, opt-in signals are sent)
Works offline-of-keys: no model/Shopify keys needed	Running the full local catalog engine (that's the private app repo)

Practical notes

Latency: a fresh recommendation runs live LLM scoring and typically takes ~20–60s. Repeat/cached contexts are faster.
Currency: all prices are CAD.
Checkout: to buy, open picksUrl and continue on presentagent.vip → secure Shopify checkout. The MCP never hands users to external retailers.
Determinism: picks are personalized and may vary slightly run-to-run as context changes.

Local context mode (opt-in)

By default the hosted server uses only what you pass in the tool call. Nothing local is read.

To let it look at local Claude/Codex/Gemini context files for soft signals about the named recipient, both must be true:

Set PRESENT_ENABLE_LOCAL_AGENT_CONTEXT=1 in the server env, and
Pass useAgentContext: true on the tool call.

When enabled, the server extracts compact preference / need / constraint hints and sends them as weak signals (never hard requirements). Secret-looking lines and paths are skipped — raw files are never transmitted. These hints are clearly labeled in the request and treated as low-confidence flavour, behind anything you state explicitly.

Configuration

All environment variables are optional — the package runs with safe defaults and no secrets. See .env.example.

Variable	Default	Purpose
`PRESENT_AGENT_CLIENT`	`unknown`	Client label for attribution (e.g. `claude-code`, `codex`).
`PRESENT_AGENT_API_BASE`	`https://presentagent.vip`	API base. Change only if self-hosting Present Agent.
`PRESENT_ENABLE_LOCAL_AGENT_CONTEXT`	unset (off)	Allow opt-in local context search (still needs `useAgentContext=true`).
`PRESENT_EXPOSE_LOCAL_AGENT_CONTEXT_LINES`	unset (off)	Echo extracted local lines in the response (debug only).

Privacy

No keys, no accounts required to use the hosted tools.
The server sends only the gift context you provide to presentagent.vip.
Local context search is off by default, double-gated, sanitized, and never transmits raw files or secret-looking content.
Requests carry an attribution label (source: "mcp", your PRESENT_AGENT_CLIENT) for analytics — no personal identifiers are added by this package.

Troubleshooting

Symptom	Fix
`failed to start` / command not found	Ensure Node.js ≥ 18 and that `npx` can reach the network on first run.
Tool call times out	Recommendations can take up to ~60s; raise your client's MCP tool timeout.
Empty / generic picks	Add a concrete interest + relationship + occasion; avoid vague input.
Want to preview Codex config	`npx -y present-agent-mcp setup codex --dry-run`

Run from source

git clone https://github.com/GuillaumeRacine/present-agent-mcp
cd present-agent-mcp
npm install
npm start            # boots the stdio MCP server

License

MIT © Present Agent. See LICENSE.

Available Tools

2 tools

present_beta_startA

Return the fastest beta onboarding instructions and live web fallback.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.5/5.0

Behavior2/5

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

With no annotations, the description must carry the full burden of behavioral disclosure. It only states the return value but omits any behavioral traits such as whether the operation is read-only, requires authentication, or has side effects. This is insufficient for a tool with zero annotation coverage.

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 a single sentence of 9 words, conveying the necessary purpose without any unnecessary words. It is optimally concise.

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?

The tool is very simple with no parameters and no output schema. The description tells what it returns. However, it lacks usage guidelines and behavioral transparency, which would be helpful for an agent to fully understand when and how to use it contextually.

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?

The tool has no parameters, and schema description coverage is trivially 100%. The description does not need to add parameter information beyond this. Baseline 4 is appropriate as the description adds no value but also does not need to.

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 returns 'beta onboarding instructions' and a 'live web fallback', with a specific verb 'Return'. It distinguishes itself from the sibling tool 'present_find_gift' which likely deals with gift-related functionality, so purpose is specific and unambiguous.

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 is provided on when to use this tool versus the sibling 'present_find_gift' or any alternative. The description does not indicate context or exclusion criteria, leaving the agent without decision-making support.

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

present_find_giftA

Find 5 personalized gifts through the hosted Present Agent API. Optional local Claude/Codex context search is opt-in.

ParametersJSON Schema

Name	Required	Description
`needs`	No	Functional needs, wishes, or outcomes the gift should support
`budget`	No	Budget: '$50-100', 'under $75', '$150 CAD', etc.
`occasion`	No	Occasion: birthday, anniversary, thank you, onboarding, housewarming, etc.
`interests`	No	Comma-separated interests, hobbies, brands, or taste signals
`recipient`	Yes	Recipient's name or short description
`constraints`	No	Hard constraints: avoid categories, delivery deadline, allergies, space, values
`preferences`	No	Known likes, style, taste, brands, hobbies, or profile clues
`relationship`	No	Relationship: partner, parent, friend, colleague, client, etc.
`giver_context`	No	Host AI memory/context about the giver: preferences, budget norms, accessibility needs, taboos, prior gifts, and personal taste. Empty if unknown; never fabricate.
`useAgentContext`	No	Opt in to local Claude/Codex/Gemini context search. Also requires PRESENT_ENABLE_LOCAL_AGENT_CONTEXT=1.
`recipient_context`	No	Host AI memory/context about the recipient beyond name/relation/occasion: life events, hobbies, prior gift outcomes, and recent notes. Empty if unknown; never fabricate.

TDQS

A3.7/5.0

Behavior3/5

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

No annotations provided, so the description carries the full burden. It mentions calling an external API and opt-in local search, but does not disclose data handling, rate limits, or any potential side effects. Partially transparent but incomplete.

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?

Two concise, front-loaded sentences. Every word adds value with no redundancy. Efficiently communicates core purpose and key behavioral note.

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 11 parameters, full schema coverage, no output schema or annotations, the description is adequate but lacks details on return format or external API behavior. It meets the minimum viability but leaves gaps for an AI agent.

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%, so the schema already documents all parameters. The description adds no extra meaning beyond mentioning the opt-in context search, which is already covered in the useAgentContext parameter description. Baseline score applies.

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 verb 'Find' and resource 'personalized gifts' with a specific count of 5. Distinguishes from sibling tool 'present_beta_start' by being the actual search/retrieval tool.

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 gift finding and notes that local context search is opt-in, but does not explicitly state when to use this tool versus the sibling or when not to use it. Lacks clear when/when-not guidance.

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. Dates show when Glama detected each change.

2 tool updatesv0.1.1Jun 25, 2026
- First observedpresent_beta_start
- First observedpresent_find_gift

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0

Scored 2026-06-25 19:20 across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one provides beta onboarding instructions, the other finds personalized gifts. There is no overlap in functionality.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern with the 'present_' prefix, making it easy to understand their actions at a glance.

Tool Count3/5

With only 2 tools, the server feels underdeveloped for an 'agent' service. While each tool has a specific function, the overall scope is limited.

Completeness2/5

The tool surface is minimal, missing obvious operations like getting more details on gifts, managing user preferences, or iterating on results. Agents are left with limited functionality.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

market A
io.github.vistoya
Search and get fashion products recommendations across multiple e-ecom stores
E-commerce & Retail Search App Automation
62
Living Stack Agent Commerce A
io.github.equinoxaifinance-rgb
Remote MCP for Living Stack offer discovery and buyer-authorized checkout preparation.
E-commerce & Retail Payments & Billing
31
ListingGood MCP A
io.github.ryanyang828
Get recommended by Amazon's AI. Hosted MCP server for Amazon listing compliance & generation.
E-commerce & Retail Marketing
821
SearchShop AI A
io.github.nathangrotticelli
AI commerce for Shopify: product search, comparison, recommendations, and checkout via MCP.
E-commerce & Retail Search AI & Machine Learning
112

Related MCP Servers

sendameal-mcp
E-commerce & Retail Search RAG Systems
McSheaD
A
license
Not graded
quality
C
maintenance
MCP server for SendaMeal.com enabling AI assistants to search gift meal products, filter by dietary restrictions, and get occasion-based recommendations. Powered by Cloudflare Workers and AutoRAG.
Updated 6 months ago (2026-03-25 11:48 UTC)
MIT
NeuronSearchLabofficial
AI & Machine Learning E-commerce & Retail
NeuronSearchLab
A
license
Not graded
quality
B
maintenance
Enables MCP-compatible AI clients to access the NeuronSearchLab recommendation engine for fetching personalized recommendations, tracking user interactions, and managing catalogue items through natural language.
Updated 7 days ago (2026-09-02 20:57 UTC)
188
MIT
menami
Menami-AI
A
license
Not graded
quality
D
maintenance
Personalized restaurant recommendations, table bookings, and delivery via MCP, CLI, or API, learning user taste and acting proactively.
Updated 5 months ago (2026-04-01 03:26 UTC)
MIT
wonderkraftz-mcp
E-commerce & Retail Search
rachit1987
A
license
A
quality
D
maintenance
An MCP server that connects AI assistants to the Wonderkraftz Premium Gifting Studio, enabling product browsing, personalized gift recommendations, cart management, and checkout through natural language.
Updated 6 months ago (2026-03-12 11:52 UTC)
12
19
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/GuillaumeRacine/present-agent-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Present Agent MCP

Quickstart

Claude Code

Codex

Any other MCP client (generic stdio config)

Tools

present_find_gift

present_beta_start

How to get the best picks

What's feasible (and what isn't)

Local context mode (opt-in)

Configuration

Privacy

Troubleshooting

Run from source

License

Available Tools

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

sendameal-mcp

NeuronSearchLabofficial

menami

wonderkraftz-mcp

Latest Blog Posts

MCP directory API

`present_find_gift`

`present_beta_start`