Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Magic Eden API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmagiceden.io%2Fmagiceden" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmagiceden.io%2Fmagiceden" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Magic Eden API.
List NFT collections and get one by its symbol
Retrieve the active listings for a collection
Get floor price and volume stats for a collection
Read trading activities for a collection or a token
Look up a token by its mint address with its listings
GET STARTED
List the tokens and activities held by a wallet address
Patterns agents use Magic Eden API for, with concrete tasks.
★ Answer NFT market questions for an AI agent
An AI agent integration created through Jentic answers questions about NFT collections. The Magic Eden API returns a collection's floor and volume stats, its active listings, and its recent activities, so the agent can report the state of a collection across supported blockchains without scraping the marketplace.
Get the stats and active listings for a collection by its symbol and summarize them
Track a wallet's NFT holdings
Portfolio tools need the NFTs a wallet holds and its recent moves. The Magic Eden API lists the tokens held by a wallet address and its activities, so an automation can build a holdings view and flag new acquisitions or sales for that wallet.
List the tokens held by a wallet address and its recent activities
Monitor a token's listings and activity
Watching a single NFT requires its listing and trade history. The Magic Eden API resolves a token by its mint address and returns its listings and activities, so an agent can watch for a price change or a sale on a specific token and act on it.
Look up a token by its mint address and return its current listings and activities
10 endpoints — the magic eden api queries nft marketplace data across multiple blockchains.
METHOD
PATH
DESCRIPTION
/collections
Get collections
/collections/{symbol}
Get a collection by symbol
/collections/{symbol}/listings
Get listings for a collection
/collections/{symbol}/stats
Get collection stats
/collections/{symbol}/activities
Get collection activities
/tokens/{token_mint}
Get a token by mint address
/wallets/{wallet_address}/tokens
Get tokens held by a wallet
/collections
Get collections
/collections/{symbol}
Get a collection by symbol
/collections/{symbol}/listings
Get listings for a collection
/collections/{symbol}/stats
Get collection stats
/collections/{symbol}/activities
Get collection activities
/tokens/{token_mint}
Get a token by mint address
/wallets/{wallet_address}/tokens
Get tokens held by a wallet
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Magic Eden API by hand means handling its bearer token and paging through collection, token, and wallet queries yourself. Through Jentic you install once, import Magic Eden from the API Directory, store the token once, and your agent calls it.
Permission scoping
Magic Eden puts the collection symbol in the URL path, so a rule can limit your agent to reading one collection's listings, stats, and activities. Every operation is read-only, so you choose which market-data operations the agent may call and no write access exists to grant.
Credential isolation
Your Magic Eden token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get collection stats' or 'list a wallet's tokens', and Jentic returns the matching Magic Eden operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Magic Eden API through Jentic.
What authentication does the Magic Eden API use?
The Magic Eden API authenticates with a bearer token in the Authorization header, per its OpenAPI spec. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's prompt or logs.
Can I get collection stats with the Magic Eden API?
Yes. The collection stats operation returns floor price and volume for a collection by its symbol, and separate operations return its active listings and recent activities, so an agent can report a collection's current state.
Can I see what NFTs a wallet holds with the Magic Eden API?
Yes. The wallet operations list the tokens held by a wallet address and its recent activities, so an agent can build a holdings view and track acquisitions or sales for that wallet.
How do I query NFT data through Jentic?
Install Jentic One on your own infrastructure with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then import the Magic Eden API from the API Directory and search for 'get NFT collection stats'. Store the token once and your agent can query collections, tokens, and wallets. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Magic Eden MCP server?
You don't need an MCP server to give your agent the Magic Eden API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls it, with operations discovered on demand instead of loaded into the agent's context.
Can I limit what my agent is allowed to do with the Magic Eden API?
Yes. Every operation here is read-only, and the collection symbol sits in the URL path, so a rule can scope the agent to reading one collection's listings, stats, and activities and nothing else. Every action it takes is recorded in an audit log.
For Agents
Query NFT collections, listings, trading activities, stats, token details, and wallet holdings on the Magic Eden marketplace.
Use for: Get the stats for an NFT collection, List the active listings for a collection, Look up a token by its mint address, Show the trading activities for a collection
Not supported: Does not mint tokens, execute trades, or custody assets. Use for reading NFT collection, token, and wallet market data only.
The Magic Eden API queries NFT marketplace data across multiple blockchains. It returns collections and their listings, trading activities, and floor and volume stats, resolves individual tokens by mint address with their listings and activities, and lists the tokens and activities held by a wallet. All operations are read-only and authenticated with a bearer token.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>