Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Entity Enricher

REMOTE · ENTITYENRICHER.AI

Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.

0 this week 81 Trust /100

Last scanned (14 hours ago)

Scores higher than 79% of remote servers

Reachable. Last reached 21 Nov 2026.

Category AI and Machine Learning

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability77
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 18131 tokens (~248/item across 73 items; 62 tools + 11 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 93% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 9 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 64 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “answer_llm_request” rewrote its description, which is the text the model reads security
    • Tool “get_job_status” rewrote its description, which is the text the model reads security
    • Tool “save_schema” rewrote its description, which is the text the model reads security
    • Tool “upload_attachment” rewrote its description, which is the text the model reads security
    • Tool “answer_job_question” is now declared destructive security
    • Tool “answer_llm_request” is now declared destructive security
    • Tool “cancel_job” is now declared destructive security
    • Tool “create_database_sync” is now declared destructive security
    • Tool “enrich_entity” is now declared destructive security
    • Tool “migrate_semantic_embeddings” is now declared destructive security
    • Tool “retry_expertises” is now declared destructive security
    • Tool “run_benchmark” is now declared destructive security
    • Tool “set_benchmark_reference” is now declared destructive security
    • Tool “start_batch_enrichment” is now declared destructive security
    • Server version: 1.30.0 → 1.27.2 functional
    • “classify_database_model” reworded the description of “use_platform_models” cosmetic
    • “create_schema_from_sample” reworded the description of “use_platform_models” cosmetic
    • “enrich_entity” reworded the description of “use_platform_models” cosmetic
    • “generate_sample” reworded the description of “use_platform_models” cosmetic
    • “merge_records” reworded the description of “use_platform_models” cosmetic
    • “retry_expertises” reworded the description of “use_platform_models” cosmetic
    • “start_batch_enrichment” reworded the description of “use_platform_models” cosmetic
  • 11 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 5 Nov 26 +1
    • Stability: 0.97 → pass security
  • 4 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 31 Oct 26 0
    • “analyze_schema” reworded the description of “model” cosmetic
    • “classify_database_model” reworded the description of “model” cosmetic

    2 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.

  • 30 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • New resource “Product support: ask Rupert” functional
    • New tool “ask_support” functional
    • New tool “get_support_conversation” functional
    • New tool “list_support_conversations” functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://entityenricher.ai/api/mcp/

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=entityenricher.ai CN=YE1,O=Let's Encrypt,C=US 14 Oct 2026 12 Jan 2027 ECDSA 256 ECDSA-SHA384 594b8f8d06d8772216b6572858cbb846513
SANs: *.entityenricher.ai, entityenricher.ai
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of entityenricher.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
entityenricher.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
x-content-type-options nosniff
x-frame-options DENY

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://entityenricher.ai/api/mcp/ Verified 200
http (plaintext) http://entityenricher.ai/api/mcp/ HTTPS enforced 301 https://entityenricher.ai/api/mcp/
MCP tools · 62 exposed · ~16,936 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
retry_expertises ~622

Retry only an existing record's failed expertise domains, then update its output and attempt the run's fusion/synchronization. Billed for retried work. Requires failed_expertises on that record (get_record); a surviving successful sibling is not retryable and returns no_failed_expertises. Supply its entity_input_data and saved_schema_id; model optionally substitutes the failed model. Returns job_id: poll get_job_status, then re-read get_record. When the failed leg left no record, use a one-model enrich_entity with database_sync=false followed by merge_records instead. Recovery decisions: enricher://docs/enrichment-and-fusion.

NameTypeReqDescription
enable_web_search––On your model (the default), true asks you to ground the answers with your own web search tool and false not to; omitted returns web_search_undecided so you ask the user first. On platform models, tr…
entity_dataobjectyesThe record's original entity input (get_record -> entity_input_data).
languages––ISO 639-1 codes; defaults to ['en'].
model––Model to retry with. Omitted (the default), the retry runs on YOUR model or, with use_platform_models=true, on the record's own model. Name a stronger provider::model (list_models) only when a domain…
reasoning_effort––Thinking (reasoning) opt-in: low, medium or high; omitted = off. On the platform, auto then picks only a model whose reasoning the platform can pilot, and the effort is translated per provider. On YO…
record_idstringyesEnrichment record with failed expertises.
schema_id––Saved schema UUID (get_record -> saved_schema_id). Or pass target_schema.
target_schema––Raw schema dict when no saved schema exists.
use_platform_modelsboolean–false (default): every LLM call of this job runs on YOUR model — the job parks each call as a pending request you answer with answer_llm_request; no credits are consumed. Attachments are no reason to…

Structured output declared, but exposes no named fields.

No examples provided.

revert_benchmark_reference_updates ~219

Undo automatic edits a scoring pass made to a scenario's reference. Every scoring pass folds what the scored models showed the reference should be (a candidate the judge found better, a rule the samples prove, a value the reference lacked) and writes it into the reference — an edit a pass already made is only replaced by stronger evidence (samples, a wrong verdict, more agreeing models), never by one more model's better verdict; the log is reference_meta.auto_applied on get_benchmark_scenario, each entry with its inverse patch. Pass the revision ids to undo: the inverse is applied, the entry is marked reverted and its (path, attribute) is pinned so no later pass re-applies it (a manual set_benchmark_reference lifts every pin). Scores never go stale from this. Requires owner and a plan with benchmarks. No LLM call.

NameTypeReqDescription
revision_idsarrayyesIds of the reference_meta.auto_applied entries to undo (1..200).
scenario_idstringyesUUID of the scenario.

Structured output declared, but exposes no named fields.

No examples provided.

run_benchmark ~231

Start billed asynchronous execution and scoring of a benchmark. Requires owner, a benchmark-enabled plan and a judge; a verified reference is also required except for sample generation. Supply model_keys or providers; omitting both runs all active models with usable provider keys. Repetitions and judging increase cost. Returns job_id and total_models: poll get_job_status, then read get_benchmark_scenario_results. Re-running replaces each selected model's previous result. An organization's benchmark runs and scoring passes execute one at a time: a launch while another is in flight is queued (queue_position, status 'pending'), and a launch on a scenario whose run is still queued folds its models into that run (merged=true, job_id names the queued run). Reference setup and score interpretation: enricher://docs/model-benchmark.

NameTypeReqDescription
model_keys––Explicit model composite keys. Overrides `providers`.
providers––Provider names (e.g. ['anthropic', 'mistral']) — runs every active model of those providers that has a valid key.
scenario_idstringyesUUID of the scenario to run.

Structured output declared, but exposes no named fields.

No examples provided.

save_schema ~414

Save a directly authored schema and return its ID and link. Mostly for a document that starts from a schema Entity Enricher generated — read with get_schema, revised, saved as a new schema or variant — or one the user already holds (an import). Not for creating a schema from scratch: to derive one from samples or data, call create_schema_from_sample instead of writing the document yourself. Its staged steps judge one question at a time (which nested objects are entities, what identifies each, expertise domains, flags, closed vocabularies), the code keeps only types that hold for every observed value, and the run is recorded with the schema, where the user watches it on the Monitor and reviews each judgement. A document written in one go skips those checks and leaves no trace of how it was decided; generation runs on your own model by default, so saving directly spares no credits. Requires editor; no LLM call. schema_content is a JSON Schema 2020-12 document in Entity Enricher's supported dialect: title, type='object', properties, optional $defs and x-* extension sections. The server validates it and makes colliding names unique. Entity definitions, enum vocabularies and localized fields have different projection rules. Unknown keywords are dropped, not rejected: read ignored_keywords (path, keyword, hint) and applied_repairs in the result — a property flag such as semantic_id placed on a $defs entity object lands there, with the level it is read at. This always creates a schema: to change one in place use update_schema or the property tools. A minimal valid example and supported annotations are in enricher://docs/schema-reference.

NameTypeReqDescription
is_pinnedboolean–Pin it to the top of listings.
namestringyes–
schema_contentobjectyesFull schema document: title, type=object, properties and optional $defs/x-* sections. See enricher://docs/schema-reference for a minimal example.
tags––Optional tags.

Structured output declared, but exposes no named fields.

No examples provided.

set_benchmark_reference ~199

Save the gold reference for an enrichment or schema-generation benchmark. Only set reference_verified=true after checking its values against trusted evidence or obtaining human sign-off; a generated answer alone is not verification. Schema-generation references must be GeneratedJsonSchema objects. Sample-generation scenarios reject references because they are rubric-scored. Requires owner and a plan with benchmarks; no LLM call. A verified reference enables run_benchmark. See enricher://docs/model-benchmark.

NameTypeReqDescription
reference_outputobjectyesExpected entity JSON for enrichment, or a schema document for schema_generation. Sample-generation scenarios do not accept a reference.
reference_verifiedboolean–Explicit sign-off that the reference is correct (required to run).
scenario_idstringyesUUID of the scenario.
source––Provenance: generated | pasted | record (default 'pasted').
source_record_id––Record UUID the reference was copied from (when source='record').

Structured output declared, but exposes no named fields.

No examples provided.

start_batch_enrichment ~787

Start billed asynchronous enrichment of an entity list against exactly one of schema_id or target_schema. Returns job_id and total. No fixed entity-count cap; live prompt quotas and credits can stop remaining work. Each entity follows the enrichment/fusion pipeline; every model must succeed for its automatic fusion and database admission. A confident classification mismatch skips that entity without enrichment, never pauses the batch. Poll get_job_status, then list_records(job_id=...). Attachments apply to every entity. Unlike enrich_entity, this tool does not expose database_sync=false. By default the job runs on YOUR model (use_platform_models=false, no explicit model): its entities park their calls as llm_requests, several at once, and enable_web_search must be decided (omitted returns web_search_undecided). Input contracts, partial results and recovery: enricher://docs/batch-enrichment.

NameTypeReqDescription
arbitration_model––Optional LLM for auto-fusion conflict resolution (None = rule-based).
attachment_ids––Attachment UUIDs applied as source material to every entity.
classification_model––Optional classifier key. Confident mismatches skip that entity; softer verdicts become prompt context. Batch classification never pauses.
enable_web_search––On your model (the default), true asks you to ground the answers with your own web search tool and false not to; omitted returns web_search_undecided so you ask the user first. On platform models, tr…
entitiesarrayyesEntities to enrich (each a free-form dict naming the entity — the schema's identifying fields ideally, but any field names work).
languages––ISO 639-1 codes; defaults to ['en'].
models––Model composite keys; omit (or pass ['auto']) for one automatically selected model: YOUR model, or with use_platform_models=true the organization's best model for enrichment from its benchmark scores…
reasoning_effort––Thinking (reasoning) opt-in: low, medium or high; omitted = off. On the platform, auto then picks only a model whose reasoning the platform can pilot, and the effort is translated per provider. On YO…
schema_id––UUID of a saved schema. Mutually exclusive with target_schema.
strategystring–auto (default) | single_pass | expert_domains | multi_expertise
target_schema––Inline schema document in the supported Entity Enricher dialect. Prefer schema_id to link records. See enricher://docs/schema-reference.
use_platform_modelsboolean–false (default): every LLM call of this job runs on YOUR model — the job parks each call as a pending request you answer with answer_llm_request; no credits are consumed. Attachments are no reason to…

Structured output declared, but exposes no named fields.

No examples provided.

sync_records_to_database ~177

Validate and inject stored or supplied enrichment output into the entity layer and linked syncs. May incur semantic-resolution cost. record_id alone reuses its output; adding structured_output creates a new derived record. Without record_id, supply structured_output and saved_schema_id. Each item uses the current published contract and admission gate. Only enrichment/arbitration records qualify; base records whose fusion is in the same request are skipped. Inspect each outcome for rejected or partial writes. Use after fixing a rejected output or an enrich_entity run with database_sync=false. See enricher://docs/enrichment-and-fusion.

NameTypeReqDescription
itemsarrayyesEntities to inject. Each item: {record_id?, structured_output?, saved_schema_id?} — at least one of record_id / structured_output, and saved_schema_id required when there is no record_id.

Structured output declared, but exposes no named fields.

No examples provided.

update_benchmark_scenario ~313

Edit a benchmark's test definition or scoring configuration. Requires owner and a plan with benchmarks; no model run. Only supplied fields change, but sample_params and schema_gen_params replace their parameter objects wholesale. The judge may be replaced, not cleared; scenario_type is immutable. Changed test definitions make previous results stale. Re-run affected models to refresh their scores. See enricher://docs/model-benchmark.

NameTypeReqDescription
description––Free-text note shown in the Benchmarks tab; no model ever reads it.
entity_data––Enrichment: replacement fixed entity input (same contract as enrich_entity's entity_data; refused when it carries no value).
entity_samples––schema_generation: replacement input samples (1..20, whole list).
languages–––
name–––
repetitions–––
sample_params––sample_generation: full replacement task params object {request, typical_object, naming_convention, language, enable_web_search}.
scenario_idstringyesUUID of the scenario.
schema_gen_params––schema_generation: full replacement task params object {generate_semantic_ids}.
schema_id––New saved-schema UUID.
scoring_judge_model_key–––
scoring_source––Feed this scenario's results into the live per-model scores of the options API: 'organization' (owner+), 'global' (system admin only, fallback for orgs without their own source), or 'off' to stop usi…
strategy–––

Structured output declared, but exposes no named fields.

No examples provided.

update_concept_alias ~148

Remove or promote a concept alias using alias IDs from get_semantic_concept. Requires editor; no LLM call. action='remove' stops that surface form resolving to this concept; removing the last alias is refused. action='set_canonical' changes its displayed form. To add an alias use add_semantic_concept(alias_of=...). Returns the outcome. See enricher://docs/semantic-ids.

NameTypeReqDescription
actionstringyes'remove' prunes the surface form; 'set_canonical' promotes it.
alias_idstringyesThe surface-form row's own id (UUID).
concept_idstringyesThe concept's semantic_id (UUID).

Structured output declared, but exposes no named fields.

No examples provided.

update_schema ~270

Edit a saved schema's metadata or replace its full schema_content without an LLM call. Requires editor. Only supplied values change. For one property, prefer update_schema_property, add_schema_property or move_schema_property. Replacements must use GeneratedJsonSchema; unknown keywords are dropped, not rejected, and reported in ignored_keywords / applied_repairs. On database-linked schemas this edits the working copy: neutral edits propagate automatically; structural edits take effect after publish_schema. Returns the updated schema and link. Contract and edit workflow: enricher://docs/schema-reference.

NameTypeReqDescription
ambiguity_check_enabled––Enable/disable the ambiguity check for this schema — the pass that flags properties whose name admits more than one meaning (gates analyze_schema and the generation post-pass).
is_pinned––Pin or unpin.
key_language––Pre-set the key language for multilingual database keys ahead of a database link (ISO 639-1). Settable only while the schema has no linked database and no entity state; locked afterwards.
name––New name (must be unique).
schema_content––Full replacement schema document, following get_schema.schema_content. See enricher://docs/schema-reference.
schema_idstringyesUUID of the schema to update.
tags––Replacement tag list.

Structured output declared, but exposes no named fields.

No examples provided.

update_schema_property ~306

Edit or remove one property by path without replacing the full schema. Requires editor; no LLM call. Only supplied fields change; null clears an entry in flags. Server validation rejects or normalizes invalid combinations and reports applied_repairs. Editing inside $defs affects every usage site. Removing an identity-source member is refused until its identity is recomposed. Renames preserve identity references and record migration intent. Database-linked schemas remain working-copy edits until publish_schema; inspect migration_grade. For additions or relocation use add_schema_property or move_schema_property. Paths, flags and rename rules: enricher://docs/schema-reference.

NameTypeReqDescription
description–––
examples–––
flags––Flag updates (null clears): expertise, preserve, multilingual, language_discriminator, identifying, nullable, format, pattern, semantic_id, judge_floor, semantic_concept_type, semantic_embedding_mode…
new_name––Rename the property.
pathstringyesProperty path, e.g. 'ceremonies[].ceremony_type'.
ref––'#/$defs/X' or '#/$enums/X'; clears type.
removeboolean–Delete the property instead.
schema_idstringyesUUID of the saved schema.
type––New JSON type (string/number/integer/boolean/array/object); clears $ref.

Structured output declared, but exposes no named fields.

No examples provided.

upload_attachment ~218

Upload base64 file bytes as reusable source material; returns id and requires_capability. Pass the ID in attachment_ids to sample/schema generation, enrichment or benchmarks. Supported format handling depends on server MIME policy: extracted text or model-readable binary. Keep the file at hand: a job running on your model (the default) names it in its requests and you read your own copy, whatever its format — no platform model is needed to read it. On platform models, leave the model on auto so the pick can read it. Uploading does not itself run an LLM. A generated sample with attachments is source-only; see enricher://docs/documents for formats, multiple-file behavior and research workflows. Retain attachments needed for later runs or regeneration.

NameTypeReqDescription
content_base64stringyesThe file's bytes, base64-encoded (no data: prefix).
filenamestringyesOriginal filename including extension (e.g. 'report.pdf').
media_type––Optional MIME hint; the server still sniffs the magic bytes.

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the Entity Enricher MCP server?

Entity Enricher is a hosted endpoint at https://entityenricher.ai/api/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · entityenricher.ai

# add to Claude Code
claude mcp add --transport http ai-entityenricher-enricher 'https://entityenricher.ai/api/mcp/'
Common questions

What is the Entity Enricher MCP server?

Entity Enricher is an MCP server listed in the public MCP registry as ai.entityenricher/enricher. Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks. This page covers its hosted endpoint (https://entityenricher.ai/api/mcp/).

Is the Entity Enricher MCP server safe to use?

Entity Enricher scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Entity Enricher MCP server expose?

Entity Enricher exposes 62 tools: upload_attachment, delete_attachment, start_batch_enrichment, list_benchmark_scenarios, get_benchmark_scenario, and 57 more. Their descriptions and schemas cost roughly 16,936 tokens of context every time the server is loaded.

Does the Entity Enricher MCP server require authentication?

No. We connected to Entity Enricher without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Entity Enricher MCP server still maintained?

Entity Enricher is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Entity Enricher MCP server?

VerifyMCP ran 13 checks on Entity Enricher, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.