1. Conduid
  2. RAG
  3. Harborclerk
MCP server · RAG

Harborclerk

· github.com/r0shi/harborclerk

An MCP server that lets AI agents query your document archive instead of uploading it — with OCR, hybrid search, and cited local-AI answers in a private, Mac-native app.

Unclaimed dockerdocument-intelligencehybrid-searchllmlocal-firstmacosmcp-serverocrpgvectorragself-hostedsemantic-search
InstallView source
34Low

Scored a month ago · breakdown

About Harborclerk

Harborclerk is an MCP server in the RAG category: an MCP server that lets AI agents query your document archive instead of uploading it — with OCR, hybrid search, and cited local-AI answers in a private, Mac-native app.

Install

From source
git clone https://github.com/r0shi/harborclerk

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (19)

kb_batch_searchRun multiple search queries in one call (max 5), grouped per query.

Parameters not published.

kb_corpus_overviewSurvey the corpus: doc types, date ranges, sample titles.

Parameters not published.

kb_document_outlineGet a document's section structure (table of contents).

Parameters not published.

kb_documents_by_dateReturn documents sorted by their effective date.

Parameters not published.

kb_entity_cooccurrenceFind which entities appear together in the same documents or chunks.

Parameters not published.

kb_entity_overviewSurvey entities in the corpus (or scoped to a single doc).

Parameters not published.

kb_entity_searchFind documents that mention a specific named entity (person, organization, place).

Parameters not published.

kb_expand_contextRead N chunks immediately before/after a given chunk_id.

Parameters not published.

kb_find_allEnumerate documents matching a query — deduped by document, with optional literal-substring filtering.

Parameters not published.

kb_find_relatedFind documents related to a given doc_id by semantic overlap.

Parameters not published.

Show all 19 tools
kb_get_documentGet a document's metadata + summary by doc_id.

Parameters not published.

kb_ingest_statusInspect a document's ingestion pipeline status (operator-facing).

Parameters not published.

kb_list_recentList the most recently-added documents in the corpus.

Parameters not published.

kb_read_documentRead the full text of a document by doc_id.

Parameters not published.

kb_read_passagesRead specific passages by chunk_id.

Parameters not published.

kb_reprocessRe-run the ingestion pipeline for a specific document.

Parameters not published.

kb_searchSearch the knowledge base by topic, keyword, or question.

Parameters not published.

kb_system_healthCheck HC's system health (PostgreSQL, storage, Tika, reranker).

Parameters not published.

kb_verify_identifierVerify a document identifier resolves to exactly one document.

Parameters not published.

Ask AI

✦

Ask AI about Harborclerk

Powered by Claude · Grounded in docs

I know everything about Harborclerk. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Harborclerk

How do I install Harborclerk?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Harborclerk safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Harborclerk still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.