Codex, Cursor, VS Code with GitHub Copilot, Claude Code, and Claude connect to the same Entity Enricher MCP server. Their agents can design schemas, enrich entities in multiple languages, fuse models, curate semantic identities, benchmark quality, synchronize relational tables to a database — on the platform's models, or on the client's own model when the job delegates its LLM calls — and ask the product's support assistant when a question is about Entity Enricher itself.
Schema validation and agreement between models do not guarantee factual accuracy or freshness. Inspect sources, failures and partial database outcomes. The MCP provides conversational access; n8n and Make provide workflow automation over the same service.
By default every start tool runs its job on your own model (use_platform_models=true, or naming a platform model, runs it on the platform's billed models instead). The job makes no platform model call and spends no credits: the model behind your MCP client — the one already holding your conversation, your documents and your connected tools — answers every model call of the job, and the platform keeps what it is good at: building the prompts, enforcing the output schema, validating and normalizing each answer, saving the records and syncing the databases.
enable_web_search where the tool takes it: omitted, it returns web_search_undecided so you ask the user first, since the search would be your own. The job pauses as soon as its first model call is ready.llm_requests on the job status: each entry is one model call in MCP sampling/createMessage shape — system prompt, messages, tools and toolChoice — with a purpose naming the step and a deadline. Binary attachments are referenced asenricher://attachments/{id} resources, never inlined; extracted text is already in the messages. A client that uploaded the file reads its own copy, so an attachment never requires a platform model.answer_llm_request. The platform validates it against the schema exactly as it validates a provider's answer; a rejected answer comes back as the same conversation with the error in a failed tool result, to fix and answer again.Protocol details and edge cases — the opt-out, the web-search decision, concurrent requests, repair requests on enrichment, attachments, timeouts — are in the Delegated LLM calls guide listed below.
OAuth lets a client connect without an API key. Entity Enricher's consent screen identifies the client, the organization, and the role granted to the connection. Access can be managed or revoked under API Keys → Connected Apps.
These examples use browser sign-in (OAuth) and the same Streamable HTTP endpoint: https://entityenricher.ai/api/mcp/, including the trailing slash. Each client has its own configuration format.
Codex shares MCP settings between its app, CLI, and IDE extension through ~/.codex/config.toml. The first command registers Entity Enricher; the login command opens browser sign-in when authentication is needed.
codex mcp add entity-enricher --url https://entityenricher.ai/api/mcp/
codex mcp login entity-enricherCursor reads project servers from .cursor/mcp.json, or personal servers from ~/.cursor/mcp.json. The remote server entry uses mcpServers; Cursor handles the OAuth sign-in flow.
{
"mcpServers": {
"entity-enricher": {
"url": "https://entityenricher.ai/api/mcp/"
}
}
}VS Code uses .vscode/mcp.json with a servers object and an explicit http transport. Starting the server makes its tools available to GitHub Copilot's agent after authorization.
{
"servers": {
"entity-enricher": {
"type": "http",
"url": "https://entityenricher.ai/api/mcp/"
}
}
}This command registers a remote HTTP server in Claude Code. The /mcp command inside Claude Code opens its connection and authentication controls.
claude mcp add --transport http entity-enricher https://entityenricher.ai/api/mcp/On claude.ai and Claude Desktop, the Connectors settings offer an "Add custom connector" action. The connector takes the server URL above and opens Entity Enricher's authorization screen. This hosted connection is configured through Connectors; claude_desktop_config.json is for local servers.
Organization access keys are created under Settings → API Keys with a chosen role. Clients can send the key in an X-API-Key header instead of signing in with OAuth. For example, this Codex configuration reads the key from an environment variable:
[mcp_servers.entity-enricher]
url = "https://entityenricher.ai/api/mcp/"
env_http_headers = { "X-API-Key" = "ENTITY_ENRICHER_API_KEY" }ENTITY_ENRICHER_API_KEY must contain the key in the environment of the process running Codex. Cursor and VS Code accept this HTTP header in their own headers configuration object. The client references above describe their supported settings.
The same request works across clients: "List my Entity Enricher schemas, then enrich Sanofi using my pharmaceutical company schema and show the saved result."The client discovers the tools and uses them to select a schema and run enrichment. Confirmation prompts, progress display, and resource access depend on the client.
62 tools cover schema authoring, enrichment, benchmarks, database sync, semantic identities and product support. They reuse backend services for validation, billing and processing. Each tool exposes its own supported parameters. Long-running work (batch enrichment, sample generation, benchmark runs) is asynchronous: the start tool returns a job_id, the client polls get_job_statusand reads the resulting records or benchmark results. Inspect failures and partial outcomes before reporting success.
| Category | Tool | Description |
|---|---|---|
| Discovery | list_models | List available model keys, nominal capabilities, languages, strategies, auto-selected defaults and organization profile_limits. |
| Schemas | generate_sample | Generate editable sample JSON from a free-text request for schema authoring. |
| Schemas | list_schemas | List saved schemas in your organization, pinned first. |
| Schemas | get_schema | Read a saved schema with its properties, annotations and input_contract. |
| Schemas | create_schema_from_sample | Generate and auto-save a schema from reviewed samples, returning schema_id, schema content and record links. |
| Schemas | save_schema | Save a directly authored schema and return its ID and link. |
| Schemas | update_schema | Edit a saved schema's metadata or replace its full schema_content without an LLM call. |
| Schemas | get_schema_part | Read only the schema fragment needed for an edit. |
| Schemas | get_enum_candidates | List observed values outside each open enum's current vocabulary, with counts from recent enrichment records. |
| Schemas | update_schema_property | Edit or remove one property by path without replacing the full schema. |
| Schemas | add_schema_property | Add a property under the root (parent_path='), an object path or '$defs.X'. |
| Schemas | move_schema_property | Move one property into the root, an object path or '$defs.X', preserving its flags and expertise. |
| Schemas | resolve_unify_proposal | Resolve one pending entity-type unification proposal from get_schema. |
| Schemas | nest_schema_region | Materialize an entity region from get_schema's x-entityMap. |
| Schemas | publish_schema | Publish a database-linked schema's working copy as the contract used by enrichment and replicas. |
| Schemas | delete_schema | Soft-delete a saved schema by UUID. |
| Schemas | analyze_sample | Analyze sample property ambiguity and relationship identity scoping before schema generation. |
| Schemas | analyze_schema | Analyze a saved schema's property ambiguity and relationship identity scoping, writing annotations to the schema. |
| Enrichment & fusion | start_batch_enrichment | Start billed asynchronous enrichment of an entity list against exactly one of schema_id or target_schema. |
| Enrichment & fusion | enrich_entity | Enrich one entity against exactly one of schema_id or target_schema, returning structured output, record_id, costs and any database outcome. |
| Enrichment & fusion | retry_expertises | Retry only an existing record's failed expertise domains, then update its output and attempt the run's fusion/synchronization. |
| Enrichment & fusion | merge_records | Fuse two or more records of the same entity into a new arbitration record. |
| Job control | get_job_status | Read a job's status, progress and compact terminal summary with persisted record IDs. |
| Job control | cancel_job | Request cancellation of a pending, running or paused LLM job. |
| Job control | answer_job_question | Resume a paused job with answers to the questions returned under pause. |
| Job control | answer_llm_request | Submit the result of one pending model call of a delegated job: a job the user started on the client's own model (every start tool's default unless use_platform_models=true or an… |
| Records & stats | list_records | List compact, paginated records in your organization, most recent first. |
| Records & stats | get_record | Read one persisted record's structured_output, entity_input_data, validation errors, expertise verdicts and metrics. |
| Records & stats | get_stats | Read organization-wide record totals, success rate, tokens and cost summary. |
| Benchmarks | list_benchmark_scenarios | List compact benchmark scenario summaries and total. |
| Benchmarks | get_benchmark_scenario | Read one benchmark scenario with per-model quality, cost and speed results. |
| Benchmarks | get_benchmark_scenario_results | Filter, rank and limit a scenario's per-model benchmark results. |
| Benchmarks | create_benchmark_scenario | Create a reusable benchmark with a mandatory scoring judge. |
| Benchmarks | update_benchmark_scenario | Edit a benchmark's test definition or scoring configuration. |
| Benchmarks | set_benchmark_reference | Save the gold reference for an enrichment or schema-generation benchmark. |
| Benchmarks | revert_benchmark_reference_updates | Undo automatic edits a scoring pass made to a scenario's reference. |
| Benchmarks | delete_benchmark_scenario | Delete a benchmark scenario and its stored results. |
| Benchmarks | run_benchmark | Start billed asynchronous execution and scoring of a benchmark. |
| Attachments | upload_attachment | Upload base64 file bytes as reusable source material; returns id and requires_capability. |
| Attachments | delete_attachment | Permanently delete an attachment in your organization, including its stored file. |
| Database Sync | list_database_syncs | List a saved schema's database registrations, linked schemas, options and sync hosts. |
| Database Sync | list_entity_states | Browse a schema's current merged entity rows, not per-run records. |
| Database Sync | create_database_sync | Register a saved schema for relational synchronization to PostgreSQL, MySQL or SQLite. |
| Database Sync | assign_sync_host | Assign or clear the host provisioning a database sync. |
| Database Sync | classify_database_model | Start a billed analysis proposing database keys, SQL types, indexes and relationship ownership on a linked schema. |
| Database Sync | delete_database_sync | Delete a database registration and its queued deltas, stopping its feed. |
| Database Sync | get_database_setup_instructions | Return non-secret install, browser-confirmed pairing and run instructions for an ee-database sync client. |
| Database Sync | fetch_database_deltas | Read the next ordered window of SQL deltas and canonical payloads for a database sync. |
| Database Sync | ack_database_deltas | Acknowledge every delta through up_to_id after successful application, releasing its lease. |
| Database Sync | sync_records_to_database | Validate and inject stored or supplied enrichment output into the entity layer and linked syncs. |
| Semantic IDs | list_semantic_concepts | Browse organization concepts with aliases, usage counts and type/model facets. |
| Semantic IDs | get_semantic_concept | Read one concept's aliases, identity source keys, linked records and nearest neighbors within its own type/model slice. |
| Semantic IDs | probe_semantic_concept | Preview identity resolution without adding a concept or increasing its usage. |
| Semantic IDs | add_semantic_concept | Add an identity concept at zero usage, or add text as an alias using alias_of. |
| Semantic IDs | update_concept_alias | Remove or promote a concept alias using alias IDs from get_semantic_concept. |
| Semantic IDs | import_semantic_concepts | Resolve 1..1000 texts against one concept type. |
| Semantic IDs | merge_semantic_concepts | Merge a loser concept into a winner. |
| Semantic IDs | delete_semantic_concepts | Delete concepts selected by ids, concept_types or unused_only. |
| Semantic IDs | migrate_semantic_embeddings | Inspect or migrate the organization's concept embedding space. |
| Product support | ask_support | Ask Rupert, Entity Enricher's product-support assistant, a question about the application itself: how a feature, a tool or a setting works, what an error_code, a limit, a status… |
| Product support | get_support_conversation | Read one of your support threads with every turn: your questions (role user), Rupert's answers (assistant) and the support team's follow-ups (admin, with author_name). |
| Product support | list_support_conversations | Your support threads, newest activity first, with message_count and unread_for_user (a support team follow-up you have not read). |
Server instructions explain the available workflows; tool descriptions explain individual calls. For modeling decisions or recovery, your client can read the guide index at enricher://docs and select a guide through MCP resources. Reading a guide does not run a model. The links below open the same English guides in the public repository.
By default every job you start runs on your own model: answer each of its model calls with `answer_llm_request`, and let the platform validate every answer against the schema. `use_platform_models=true` runs the job on the platform instead, on the organization's benchmark-best model for the task.
Design a reusable schema from reviewed examples, including identity, relationships and multilingual fields.
Read, author and edit Entity Enricher schema documents without confusing serialized JSON Schema, sample data and property-tool paths.
Choose extraction, knowledge enrichment or a two-pass combination, and preserve attachment provenance across calls.
Enrich an entity, interpret its actual outcome and recover partial model failures without repeating successful work.
Enrich an entity list asynchronously and distinguish skipped, failed, fused and database-admitted results.
Compare models on enrichment, sample generation or schema generation, using the correct reference and score interpretation.
Turn enrichment schemas into relational tables in your own database and verify admission, migration and replica delivery separately.
Recognize recurring entities across surface forms, review uncertain matches and understand how vocabulary changes affect replicas.
Ask Rupert, the product-support assistant, any question about Entity Enricher itself, continue the thread you opened, and read the support team's follow-ups.
Resources expose schema and record data, plus workflow guides, as Markdown. Clients choose how to discover and load them; resource content can still consume model context.
| URI template | Description |
|---|---|
| enricher://docs | Index of the workflow guides, each available at its listed resource URI. |
| enricher://schemas/{schema_id} | A saved schema working copy as Markdown; use get_schema with version="published" for the active linked contract. |
| enricher://records/{record_id} | A past enrichment record rendered as Markdown — metadata + structured output + validation errors. |
| enricher://attachments/{attachment_id} | The bytes of an uploaded attachment, served with their real media type — how a job that delegates its LLM calls hands your client a PDF, image or audio file it did not upload itself. |
When a question is about Entity Enricher itself — how a feature or a tool works, what an error code, a limit or a warning means, why a result looks the way it does — and the guides do not answer it, the server instructions tell the agent to ask Rupert, the product-support assistant, with ask_support rather than guess. The call returns the complete answer and the id of the thread it opened; passing thatconversation_id to the next question keeps the context of the exchange.
Each question counts against the organization's daily support quota, reported asquestions_remaining. The support team may answer in the thread: the next ask_support on it returns those follow-ups asnew_admin_messages, andget_support_conversation reads a whole thread. The same threads appear in the web app's support chat and, for owners, in the Users page's Discussions tab, badged as opened by an AI agent.
When you ask enrich_entity to use a classification model and the entity doesn't match the schema type, the tool returns anon-error response with structured details. The client reads it, surfaces the reasoning to you, and (on your confirmation) retries with force_after_classification_warning=true — which drops the classifier on the retry.
{
"success": false,
"error_code": "classification_warning",
"message": "Pre-flight classification rejected the entity. ...",
"classification": {
"status": "mismatch",
"reasoning": "Titan is a moon of Saturn, not a planet.",
"confidence": 0.97
},
"job_id": "..."
}The MCP response preserves the classification details so your client can explain the decision before starting a new call.
The same interactivity powers a second flow: when generate_sample runs with source documents, its planner may pause with structural clarification questions. The client relays them to you and resumes the job with answer_job_question — round after round, until the sample is generated.
Most tool errors return a structured object with an error_code field so the client can distinguish quota, classification, timeout and provider failures. Some older responses carry only an error or message field; inspect the actual result as well as the transport status.
| error_code | When |
|---|---|
| invalid_request | Malformed UUID, mutually exclusive args (schema_id + target_schema), or request body validation failed. |
| prompt_limit_reached | Daily / weekly / monthly prompt quota exhausted (HTTP 402). Body includes period, limit, used, needed. |
| insufficient_credits | Org has billing enabled but credit balance is too low to start the job (HTTP 402). Body includes balance and a purchase URL. |
| model_limit_exceeded | Asked for more models than the plan allows (HTTP 402). Echoes limit + requested. |
| language_limit_exceeded | Asked for more languages than the plan allows (HTTP 402). |
| concurrent_job_limit_reached | Too many active enrichment jobs for this org. Wait or upgrade plan. |
| classification_warning | ⚡ Non-error: pre-flight classifier rejected the entity. Response carries the classification context so the client can ask the user to confirm and retry with force_after_classification_warning=true. |
| benchmarks_not_in_plan | The organization plan does not include Model Benchmarks (HTTP 403). Mutating benchmark tools also check the owner role. |
| support_question_limit_reached | The organization's daily support-question quota is spent (HTTP 402). Body includes limit and used; every ask_support result reports questions_remaining. |
| support_requires_user | ask_support was called with an organization access key (HTTP 403). A support thread belongs to a person: sign in with OAuth or a personal API key. |
| support_unavailable | The support assistant could not answer (relay failure). The question still counts and the thread exists: read it later with get_support_conversation rather than asking again at once. |
| web_search_undecided | A start tool was called without enable_web_search for a job running on your model. Ask the user whether your model may use web search, then call again with enable_web_search=true or false. |
| delegation_requires_auto | A job running on your model met an explicit platform model injected after launch, such as an organization default (HTTP 400). Start the job with use_platform_models=true, or drop that default. |
| request_not_pending | answer_llm_request named a request that was already answered, expired, or belongs to a job that moved on. Read get_job_status(job_id).llm_requests for what is pending now. |
| llm_request_pending | answer_job_question was called on a job paused on delegated LLM requests, not on a question. Answer them with answer_llm_request. |
| llm_request_timeout | A job delegating its LLM calls got no answer to a pending request within 15 minutes; the job failed. Delegated jobs have no default answer. |
| ambiguity_check_disabled | analyze_schema was called on a schema whose ambiguity check is toggled off (HTTP 400). Re-enable it via update_schema with ambiguity_check_enabled=true first. |
| enrichment_timeout | Job exceeded timeout_seconds. Suggest fewer models or splitting the entity. |
| schema_generation_timeout | Schema generation exceeded timeout_seconds. |
| schema_generation_failed | Upstream LLM error during schema generation (HTTP 502). |
| model_output_invalid | The model returned output that does not match the schema (HTTP 502). Body names the model, the offending property path, and retryable: true — call the tool again, or pick a stronger model. |
| cancelled | Job was cancelled mid-run (HTTP 499). |
| not_found | Schema or record ID does not exist in your org. |
| http_error | Catch-all for HTTP errors without a structured detail body. |
get_stats covers chat-side summaries; the full dashboards stay in the app.