BIA Edge

Report corpus coverage, freshness, and inventory metadata for routing decisions. Use this before time-sensitive, current-policy, recent-case, unpublished, or visa-bulletin research, and to discover valid category slugs, source codes, and corpus-wide counts. It is a planning/inventory check, not a source retrieval tool. The default summary view is intentionally compact; use view="detail" with section/limit/offset for bounded freshness pages, or section='categories'/'sources'/'database_stats' for corpus inventory.

get_corpus_info

Get one state or federal criminal-code provision's text and metadata. Use this after lookup_criminal_code returns a provision_id; the provision's own jurisdiction determines the response, so no jurisdiction parameter is needed.

get_criminal_code_provision

Get metadata and extracted text for a federal district court decision. Args: document_id: The document ID from search_district_court_decisions or search_cases max_chars: Maximum extracted-text characters to return (default 12000, max 50000)

get_district_court_decision

Return a reviewed precedent-only doctrine family. Args: slug_or_code: Doctrine slug, code, or exact name. case_limit: Maximum linked precedent holdings to include. authority_limit: Maximum leading authority role rows to include. edge_limit: Maximum reviewed relationship rows to include.

get_doctrine_family

Return reviewed doctrine families for a precedential case document. Each family includes reviewed/published status fields plus matched_case_edges oriented around document_id, with subject_* fields for the requested case and related_* fields for the other precedent. Related precedent buckets use a compact item-ref shape; read relationship_item_index[item_id] when full evidence/rationale text is needed. Args: document_id: BIA Edge document id from search_cases/get_document. family_limit: Maximum doctrine families to return. case_limit: Maximum case memberships to include per family. authority_limit: Maximum leading authority rows per family. edge_limit: Maximum reviewed case-to-case relationships per family.

get_doctrine_by_case

Get a case/document by database ID: metadata, full text, headnotes, and/or holdings. include='metadata' (default) returns case name, citation, date, deciding body, summary, source, court, outcome, word count, and ImmCite validity status. ImmCite status values: valid (stored good_law normalizes to valid), caution, negative, overruled, vacated, reinstated, unchecked, unchecked_no_treatment_data, and not_applicable. include='text' returns the full extracted decision text (truncated to max_chars); use it when you need to read the actual decision, not just metadata. include='headnotes' / include='holdings' return AI-extracted headnotes and holdings (derived metadata; verify propositions against source text before relying). Combine sections with commas. Args: document_id: The document ID (from search results or citation lookups) include: Comma-separated sections: metadata, text, headnotes, holdings. max_chars: Maximum text characters when include contains 'text' (default 15000, max 100000) ImmCite status vocabulary: valid, caution, negative, overruled, vacated, reinstated, unchecked, unchecked_no_treatment_data, not_applicable. Stored good_law normalizes to valid. unchecked means an eligible authority has no stored public status; unchecked_no_treatment_data is the MCP explanation for eligible authorities with no treatment row; not_applicable means the document is outside the precedential ImmCite corpus.

get_document

Return one EOIR judge's or court's descriptive statistics profile with denominators. This is an analytics primitive: it surfaces metrics, denominators, source hash, and caveats. It does not provide legal strategy, forum-shopping guidance, or judge predictions.

get_eoir_profile

Rank immigration cases by citation count within the BIA Edge corpus. This is a corpus citation-count ranking, not an editorial judgment that a case is legally controlling, important, or still good law. Args: source: Filter by source: 'bia', 'aao', 'ag', 'circuit-courts' limit: Max results (default 25)

get_most_cited

Fetch exact evidence spans by IDs returned from search_passages. Args: span_ids: Span IDs such as case:123:issue_unit:456 or case:123:block:789.

get_passages

Get full text for a reference-section record. Args: reference_id: The reference section ID (from search_references results) max_chars: Max characters of full text to return (default 15000) section: Optional heading/subsection title to retrieve from a long reference

get_reference

Resolve a known USCIS, FAM, form-instruction, or practice-reference citation. Use this before search_references when the citation or source label is known. Use find_in_reference for pinpoint snippets or fetch for larger section text after a reference is resolved.

get_reference_by_citation

Get recent regulatory and policy changes in immigration law. Includes new BIA/AG decisions, CFR amendments, policy manual updates, and Federal Register notices. Args: days: Look back period in days (default 30) limit: Max results (default 20)

get_regulatory_updates

Return reviewed related precedent holdings for a case. Results are oriented around document_id: subject_* fields identify the requested case, related_* fields identify the connected precedent, relationship_status confirms the reviewed edge status and relationship_summary states the reviewed relationship. To keep inline tool output compact, leading/related/adverse lists and relationship_buckets are lightweight item refs with an item_id. Read relationship_item_index[item_id] only when full evidence/rationale text is needed. relationship_taxonomy documents every supported reviewed relationship type and how clients should bucket it. relationship_types is a comma-separated optional filter, e.g. defines, applies, limits, distinguishes, overrules, follows, cited_favorably, cited_negatively. Args: document_id: BIA Edge document id. relationship_types: Optional comma-separated relationship type filter. limit: Maximum relationship rows to return, up to 100.

get_related_precedent_holdings

Get the BIA Edge legal-research playbook to follow for serious research. Fetch and follow deep_research_method before filing-facing work: legal memos, briefs, authority packets, RFE/NOID support, crimmigration screens, or any research where a wrong answer creates filing or malpractice risk. Fetch unpublished_routing before searching unpublished BIA/AAO decisions. Fetch authority_taxonomy when classifying binding vs. non-precedent authority. Fetch research_method for the overall method: request-mode classification, operating principles, research floors, validity-check discipline, memo structure, and citation rules. Returns the requested section as markdown, with the list of available sections. The playbook is methodology, not law: it tells you how to research and present authority, and the direct source tools remain the only source of legal content. Args: section: Which playbook section to return (default research_method).

get_research_playbook

Get the full text of a specific statutory or regulatory provision. Args: provision_id: The provision ID (from search_statutes results)

get_statute

Resolve a known INA, USC immigration, or CFR citation. Use this before search_statutes when the citation is known. Use lookup_criminal_code(jurisdiction='federal') for Title 18 and other federal criminal-code provisions instead of treating a statute search miss as absence.

get_statute_by_citation

Return Visa Bulletin priority dates loaded in BIA Edge, or check one priority date. Without priority_date, returns the stored bulletin table (omit month/year for the latest loaded bulletin, or provide both for a historical month). With priority_date plus category and chargeability, answers whether that date is available under the selected chart. Use this for stored priority-date research, not case-law research; call get_corpus_info or verify official Department of State sources when the latest bulletin timing matters. Record metadata includes final_action_status and dates_for_filing_status with values current, unavailable, not_published, or date; date fields are null for non-date rows.

get_visa_bulletin

List the organized district-court decision families and live corpus counts. Use this before district-court MCP searches when you need to choose a practitioner-facing corpus slice. The listed decisions are nonprecedential federal district court decisions and are persuasive only.

list_district_court_decision_families

Search state or federal criminal-code provisions for crimmigration research. Use this before categorical-approach analysis to find the statute of conviction by citation, section number, title, or text. Results include official-source status, parser/ingestion status, and the text for the best match when available. State coverage is penal-title-only for some states, so a miss is not proof a state offense does not exist; the empty response lists the official source records BIA Edge holds. search_statutes is the immigration statute/regulation lane and is not proof of criminal-code absence. Use get_criminal_code_provision after lookup when you need one provision's full text and metadata.

lookup_criminal_code

Lookup current USCIS form-page and form/instruction PDF records. Args: form_number: USCIS form number such as I-751, I-90, I-485, I-765, or N-400. max_chars: Maximum source snippet characters per returned source. Defaults compact; use returned reference_id values with get_reference or find_in_reference for full source text.

lookup_uscis_form

Query EOIR statistics rollups as descriptive analytics data. This read-only primitive returns facts, denominators, filters, and caveats. It intentionally does not produce legal strategy, judge predictions, or recommendations.

query_eoir_stats

Optionally resolve current USCIS policy/guidance source candidates. This is a bounded convenience wrapper. Capable agents should use exact statute/reference lookups and source_code-filtered search_references for authoritative research, then use this only to assemble current-source leads.

resolve_current_uscis_policy

Generic structured search for ChatGPT/Codex MCP clients. Case results may include ImmCite validity_status values. ImmCite status values: valid (stored good_law normalizes to valid), caution, negative, overruled, vacated, reinstated, unchecked, unchecked_no_treatment_data, and not_applicable. Args: query: Search text. corpus: all, cases, references, statutes, unpublished, or categories. limit: Maximum results per requested corpus (1-25). ImmCite status vocabulary: valid, caution, negative, overruled, vacated, reinstated, unchecked, unchecked_no_treatment_data, not_applicable. Stored good_law normalizes to valid. unchecked means an eligible authority has no stored public status; unchecked_no_treatment_data is the MCP explanation for eligible authorities with no treatment row; not_applicable means the document is outside the precedential ImmCite corpus.

search

Search immigration case law with Vespa-backed ranking. Use this for names, concepts, or keywords when there is no known citation. Use get_case_by_citation first for a known citation, then bridge central cases to document_id for check_validity or corpus source-text tools. ImmCite status vocabulary: valid, caution, negative, overruled, vacated, reinstated, unchecked, unchecked_no_treatment_data, not_applicable. Stored good_law normalizes to valid. unchecked means an eligible authority has no stored public status; unchecked_no_treatment_data is the MCP explanation for eligible authorities with no treatment row; not_applicable means the document is outside the precedential ImmCite corpus.

search_cases

Search asylum country-condition reports. Searches State Department Country Reports on Human Rights Practices, International Religious Freedom Reports, and Trafficking in Persons reports after those sources are loaded into the reference corpus. Args: country: Optional country name, e.g. "Afghanistan" or "Mexico" query: Optional issue terms, e.g. "political opinion", "FGM", "police torture" report_type: Optional type: hrr/human_rights, irf/religious_freedom, tip/trafficking, or all year_from: Optional earliest report year to include year_to: Optional latest report year to include. Omit to search through the newest loaded report year. limit: Max results

search_country_conditions

Search nonprecedential federal district court immigration decisions. Use this for written federal district judge opinions and orders, including mandamus / agency-delay, immigration habeas, naturalization, USCIS benefits APA review, consular/visa, immigration FOIA, and other civil immigration decisions. The 'mandamus' category is a posture-based lane across subject families. These decisions are persuasive only and are kept out of ordinary precedential search unless district-court material is explicitly requested. Args: query: Search text - issue, agency, party name, docket number, or keywords decision_category: Optional corpus slice, such as 'mandamus', 'habeas', 'naturalization', 'benefits', 'consular', 'foia', 'u_visa', or 'other' court: Optional district court code, such as 'txsd', 'txnd', 'cacd', 'dcd', or 'nysd' date_from: Start date (YYYY-MM-DD) date_to: End date (YYYY-MM-DD) limit: Max results (1-50, default 20)

search_district_court_decisions

Search reviewed precedent-only doctrine families. Returns only approved/published doctrine nodes and membership counts. Use this before broader case searching when the user asks for a doctrine family, related precedent, limiting authority, or how holdings connect. Args: query: Optional doctrine name, code, slug, or descriptive query. limit: Maximum doctrine families to return, up to 50.

search_doctrines

Search EOIR immigration judges and return descriptive rollup statistics. This is an analytics primitive. It surfaces denominators, filters, source hash, and caveats; it does not rank judges for case strategy or make judge predictions. When court_code is supplied, returned list metrics are scoped to detail rollups at that court; use get_eoir_profile for career-wide context.

search_eoir_judges

Search materialized source-text spans and issue units. Returns compact evidence records with stable span IDs, offsets, source text, authority metadata, and match reasons. Use this before fetching full cases when the agent needs pinpoint support for a proposition. AAO non-precedent paragraph spans are retrieval-only persuasive support and are returned only when authority_scope='all' is selected; the default precedential scope keeps them out of binding-law searches. Args: query: Legal terms, factual phrase, statutory phrase, or quoted language. source: Optional source filter such as bia, ag, aao, circuit-courts, scotus. document_id: Optional document ID to search within one authority. authority_scope: all, precedential, or binding. Default excludes known nonprecedential material. granularity: passage for source-text paragraphs, issue for holdings/headnotes, or all. limit: Maximum spans to return, up to 50.

search_passages

Search USCIS, FAM, practice-manual, and asylum reference materials. Use this for policy or guidance issues when the exact citation is unknown. Use get_reference_by_citation for known references and find_in_reference or fetch for pinpoint source text after a reference section is identified.

search_references

Search INA, USC immigration, and CFR statute/regulation provisions. Use this when the exact citation is unknown or the request is conceptual. Use get_statute_by_citation first for a known INA/USC/CFR citation. Use lookup_criminal_code(jurisdiction='federal'), not this tool, for Title 18 and other federal criminal-code provisions.

search_statutes

Search non-precedential BIA and AAO decisions. Use this for non-binding candidate support after controlling authority is framed, and source-text check candidates with fetch or corpus text tools before relying on them. favorable_only=true restricts results to decisions whose stored direction verifies the immigrant won or DHS/USCIS lost; the tag is derived metadata, so verify direction against source text. For a primary unpublished lane, pass an explicit source; unscoped or inferred-source results are candidates only and must not be treated as completed legal research.

search_unpublished_cases