Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the FXNewsBias 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%2Ffxnewsbias.com%2Ffxnewsbias" | 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%2Ffxnewsbias.com%2Ffxnewsbias" | 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 FXNewsBias API.
Read current sentiment scores for the 8 major currency pairs, refreshed every 3 hours
Pull historical sentiment scores for the majors
Read the settled session-bias scorecard and its history
Read Gold and other market sentiment on the Pro Markets endpoints
Check the caller's tier, daily allowance, and spend
GET STARTED
Patterns agents use FXNewsBias API for, with concrete tasks.
★ AI Agent Sentiment Lookup via Jentic
An AI agent reaches FXNewsBias through Jentic to read a directional read on the majors without wiring the bearer key itself. It searches by intent, receives the matching operation and its input schema, and executes the read with the key injected at run time. This lets the agent fold a fresh sentiment score into a trading or research decision.
Search Jentic for 'current FX sentiment for the majors', load the GET /api/v1/sentiment schema, and execute it with the key injected at run time
Sentiment-Driven Trade Bias
A trading workflow sets a directional bias on a currency pair before placing a trade elsewhere. FXNewsBias returns the current sentiment score for the majors and the newest session-bias call, so an agent can confirm news tone and session positioning agree before it acts. The scores refresh every 3 hours, which bounds how often the bias can move.
Call GET /api/v1/sentiment for current scores and GET /api/v1/session-bias for the newest session bias to set a directional bias
Backtesting Sentiment Signals
A quant workflow tests whether sentiment and settled session bias have predicted the majors. FXNewsBias returns historical sentiment scores and the settled session-bias history, so an agent can line past signals up against realized moves. Because the v1 response shapes are frozen, a backtest built today keeps parsing tomorrow.
Call GET /api/v1/sentiment/history and GET /api/v1/session-bias/history to pull past scores and settled calls for a backtest
Gold Market Monitoring
A metals-focused workflow watches Gold sentiment on the Pro Markets endpoints, which sit apart from the eight-pair core response. FXNewsBias returns the latest read for every market and the newest session call for one market, so an agent can track XAU/USD without disturbing the majors feed. Historical market reads support the same backtesting flow.
Call GET /api/v1/markets for the latest read on every market, then GET /api/v1/markets/session-bias for the newest Gold session call
9 endpoints — the fxnewsbias api serves news-sentiment scores for the eight major currency pairs, refreshed every 3 hours, alongside a settled session-bias scorecard.
METHOD
PATH
DESCRIPTION
/api/v1/sentiment
Current sentiment for the 8 majors
/api/v1/sentiment/history
Historical sentiment scores
/api/v1/session-bias
Session bias for the newest session
/api/v1/session-bias/history
Settled session bias history
/api/v1/markets
Latest read for every market (Pro)
/api/v1/markets/session-bias
Newest session call for one market (Pro)
/api/v1/usage
Your tier, allowance, and spend today
/api/v1/sentiment
Current sentiment for the 8 majors
/api/v1/sentiment/history
Historical sentiment scores
/api/v1/session-bias
Session bias for the newest session
/api/v1/session-bias/history
Settled session bias history
/api/v1/markets
Latest read for every market (Pro)
/api/v1/markets/session-bias
Newest session call for one market (Pro)
/api/v1/usage
Your tier, allowance, and spend today
What agents get from Jentic-routed access to this vendor.
Setup
Wiring FXNewsBias by hand means sending the bearer header with an fxnb_live_ key and watching your tier and daily allowance from the usage endpoint yourself. Through Jentic you install once, import FXNewsBias from the API Directory, store the key once, and your agent calls it.
Permission scoping
FXNewsBias carries its targets in the request rather than the URL path, so scoping is by operation: a rule can limit your agent to the specific reads it needs, such as the current sentiment and session-bias calls. You choose which operations it may call, so the Pro market reads and the history endpoints are not reachable unless you add them.
Credential isolation
Your FXNewsBias key 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 'current FX sentiment' or 'settled session bias', and Jentic returns the matching FXNewsBias 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 FXNewsBias API through Jentic.
What authentication does the FXNewsBias API use?
The FXNewsBias API authenticates with a bearer token per its OpenAPI spec: you send an Authorization header carrying an fxnb_live_ key, and the header is the accepted form, since keys are never read from the URL or query string. Creating a new key replaces the previous one. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never reaches the agent.
What are the rate limits for the FXNewsBias API?
The OpenAPI spec does not publish a numeric request limit. The usage endpoint reports your tier, daily allowance, and spend today, so an agent can read its remaining allowance before a batch of calls. See https://fxnewsbias.com/developers for current tiers.
Can I read FX sentiment scores with the FXNewsBias API?
Yes. GET /api/v1/sentiment returns current sentiment for the 8 major pairs, refreshed every 3 hours, and GET /api/v1/sentiment/history returns past scores. The settled session-bias scorecard is available from GET /api/v1/session-bias and its history endpoint.
Is there an FXNewsBias MCP server?
You don't need an MCP server to give your agent FXNewsBias. Jentic connects it directly from the API Directory: import it and your agent calls the sentiment and session-bias operations on demand, discovering each operation's schema when it needs it rather than loading a separate server's tool definitions into context.
How do I read current FX sentiment with the FXNewsBias API through Jentic?
Search Jentic for 'current FX sentiment for the majors', and it returns the FXNewsBias sentiment operation with its input schema. Load it and execute GET /api/v1/sentiment with the key injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the FXNewsBias API?
Yes. Because every operation is a read-only GET, write a rule that allows only the reads a task needs, for example the current sentiment and session-bias operations, so the agent cannot reach the Pro market reads or the history endpoints. Every call runs through your own instance, so each one is logged for you to review.
For Agents
Read news-sentiment scores for the eight major currency pairs and a settled session-bias scorecard, with history and Pro market reads for Gold and other instruments. All operations are read-only GETs secured with a bearer key.
Use for: Get the current sentiment for the 8 major pairs, Retrieve historical sentiment scores for a currency pair, Read the settled session-bias scorecard, Check the Gold market sentiment on the Pro endpoints
Not supported: Does not handle trade execution, price quotes, or economic calendars. Use for reading FX news-sentiment and session-bias scores only.
The FXNewsBias API serves news-sentiment scores for the eight major currency pairs, refreshed every 3 hours, alongside a settled session-bias scorecard. Current and historical sentiment and session-bias reads let an agent set and backtest a directional bias on the majors. Gold (XAU/USD) and other markets are served on separate Pro Markets endpoints so the core sentiment response keeps exactly eight rows. A usage endpoint reports the caller's tier, daily allowance, and spend, and the v1 response shapes are frozen so integrations stay stable.
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>