Dandelion API MCP integration for AI agents.

Connect AI agents to Dandelion API through 4 structured actions, including analyze sentiment, compare text similarity, and detect language. Review authentica…

ACTION CONTRACTS
4
AUTHENTICATION
API key
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the Dandelion API integration exposes

The Dandelion API Agent App exposes 4 provider-backed actions for ai and data work. Its current contract lets an authorized agent analyze the sentiment expressed by plain text with dandelion, compare the semantic similarity of two plain texts with dandelion, and detect the languages present in plain text with dandelion. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.

For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Dandelion API account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real Dandelion API capabilities.

Showing 4 of 4 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

analyze_sentimentREVIEW

Analyze the sentiment expressed by plain text with Dandelion.

INPUTS: text / language

compare_text_similarityREVIEW

Compare the semantic similarity of two plain texts with Dandelion.

INPUTS: firstText / secondText / language / bagOfWords

detect_languageREVIEW

Detect the languages present in plain text with Dandelion.

INPUTS: text / clean

extract_entitiesREVIEW

Extract linked entities and their positions from plain text with Dandelion.

INPUTS: text / language / minimumConfidence / maximumEntities / include

INPUT CONTRACTS

Know what the action needs before it runs.

analyze_sentiment

textREQUIRED
The plain text to analyze.
languageOPTIONAL
The ISO 639-1 language code. Omit it to let Dandelion detect the language.

compare_text_similarity

firstTextREQUIRED
The first plain text to compare.
secondTextREQUIRED
The second plain text to compare.
languageOPTIONAL
The ISO 639-1 language code. Omit it to let Dandelion detect the language.
bagOfWordsOPTIONAL
Whether to compare the texts as bags of words instead of preserving word order.

detect_language

textREQUIRED
The plain text to analyze.
cleanOPTIONAL
Whether Dandelion should remove URLs, email addresses, hashtags, and mentions before detection.

extract_entities

textREQUIRED
The plain text to analyze.
languageOPTIONAL
The ISO 639-1 language code. Omit it to let Dandelion detect the language.
minimumConfidenceOPTIONAL
The minimum entity confidence from 0 to 1.
maximumEntitiesOPTIONAL
The maximum number of top entities to include in addition to annotations.
includeOPTIONAL
The optional entity detail groups to include.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Analyze Sentiment

Analyze the sentiment expressed by plain text with Dandelion. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

analyze_sentiment

Verify with Compare Text Similarity

Compare the semantic similarity of two plain texts with Dandelion. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

compare_text_similarity

SAFETY BOUNDARY

Operate Dandelion API with explicit limits

  • Authorize Dandelion API with API key and grant only the provider access required by the selected actions.
  • The current action names appear read-oriented, but returned Dandelion API data may still be sensitive and should be minimized before it enters model context.
  • Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
  • No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Dandelion API rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the Dandelion API task completed successfully.

CONNECTION MODEL

API key

Dandelion API token. Create and manage it at https://dandelion.eu/profile/plans-and-pricing/.

Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.

READ SIGNALS
0
WRITE SIGNALS
0
HIGH IMPACT
0
REVIEW SIGNALS
4

EVIDENCE AND AVAILABILITY

Provider reference

Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Dandelion API.

Official Dandelion API website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS