Connect your AI assistant

Veterans’ Rights runs a free public Model Context Protocol (MCP) server. Point Claude, ChatGPT, an IDE, or any MCP client at it and your assistant can ground its answers in real Board of Veterans’ Appeals decisions — what was claimed, what the Board decided, and why — instead of guessing.

It is read-only, needs no API key or account, and is rate-limited for fairness (30 requests/minute per IP). Every result carries a link back to the source page here and the same standing disclaimer the site uses: educational information, not legal advice, not the VA.

Connect

The 10 tools

This list renders from the same registry the server itself serves, so it always matches what your assistant sees.

• search_bva_decisions

  Search the incomplete historical Board of Veterans’ Appeals archive using English full-text websearch over summaries, reasoning and condition text, with exact condition and optional disposition, exposure, theory, PACT Act and date filters. Full-text matching is not literal substring matching. Returns up to 25 recent matching decisions, not a total count. New imports are paused; archive ends April 30, 2026. Summaries are AI-assisted; verify each issue against the original VA source.

  Parameters: query?, condition?, disposition?, exposure_basis?, service_connection_theory?, is_pact_act?, date_from?, date_to?, limit?

• find_similar_appeals

  Find source-linked recent Board decisions mentioning one or more canonical conditions. Resolves exact names, slugs and aliases; inspects at most the 50 most recent indexed decisions per condition, then applies optional decision-level filters. Results are research examples, not a representative sample, complete filtered cohort, condition-specific outcomes or chances of winning. Grant rates are withheld. Verify each issue against the original Board decision.

  Parameters: conditions, service_connection_theory?, exposure_basis?, is_pact_act?, sample_limit?

• check_presumptive_conditions

  Check whether a condition may be a PRESUMPTIVE service connection for a veteran — meaning VA presumes it is service-connected for qualifying service/exposure, so no medical nexus needs to be proven. Covers Agent Orange/herbicides, PACT Act burn pits & airborne hazards, Camp Lejeune water, ionizing radiation, and Gulf War illness. Returns who qualifies, the legal basis, representative conditions, and how many vetted BVA decisions granted on this basis. Lists are representative, not exhaustive; educational only.

  Parameters: condition?, exposure_basis?

• explain_appeal_options

  Explains the VA review options for a decision stage. Initial/Supplemental, Higher-Level Review and final Board decisions have different options, and a preference for a hearing or new evidence does not establish eligibility. Tailored options are returned only when the decision stage and ordinary modernized-review eligibility are confirmed; unknown, legacy, contested, remand-only and pending-review contexts return general information without tailored lanes. Does not calculate personal deadlines. Educational only.

  Parameters: decision_stage?, eligible_review_context_confirmed?, has_new_evidence?, wants_hearing?

• find_accredited_rep

  Finds VA-accredited representatives for a disability claim or appeal, filtered by state, city and type. Results list free Veterans Service Organization (VSO) representatives first, then accredited claims agents and attorneys. Attorneys and agents may generally charge for work after notice of the initial VA decision, subject to VA fee rules and a written agreement. Not legal advice; not affiliated with the VA.

  Parameters: state?, city?, rep_type?, limit?

• estimate_combined_rating

  Calculate a veteran’s VA combined disability rating from individual ratings, using the official whole-person formula (38 CFR § 4.25) — ratings do NOT add (e.g. 50% + 30% combines to 65% and rounds to 70%, not 80%). Supports the bilateral factor for paired-limb disabilities (§ 4.26). Returns the exact combined value, the final rating rounded to the nearest 10, and a step-by-step breakdown. Deterministic estimate for education; VA controls the official rating.

  Parameters: ratings

• get_claim_process

  Plain-English guide to the 8 stages of a VA disability claim, from Intent to File through the C&P exam, the rating decision, the three AMA review lanes, the Board of Veterans’ Appeals, and the 120-day deadline to appeal to the Court of Appeals for Veterans Claims. With no arguments, returns an overview of all stages with typical durations; with a stage number (1–8), returns that stage in depth: what to expect, typical timing, a key tip, and do/don’t guidance. Covers what happens after filing, what a C&P exam is, and what each stage involves. Educational only, not legal advice.

  Parameters: stage?

• get_corpus_stats

  Returns current statistics about the Veterans’ Rights archive: the number of vetted Board of Veterans’ Appeals decisions, the distribution of outcomes (granted / denied / remanded / mixed), the date range the decisions cover, and the number of accredited representatives in the directory. Shows how much data the archive holds and how current it is. Counts reflect only quality-filtered, publicly visible decisions.

  Parameters: none

• list_conditions

  Lists the standardized conditions the Veterans’ Rights archive organizes Board of Veterans’ Appeals decisions under, each with its slug, body-system category and full-archive counts of vetted decisions, grants and remands. Counts describe whole decisions mentioning each condition, not condition-specific wins or individual chances. Counts reflect only quality-filtered, publicly visible decisions.

  Parameters: none

• get_condition_report

  For a single condition (by slug like "ptsd" or "sleep-apnea", or by common name/alias like "PTSD", "acid reflux", "ringing in the ears"), return a full corpus-grounded report: how Board decisions mentioning it turned out (whole-decision granted / partly granted / remanded / denied), decision-level service-connection theory labels, an explicit decision-level attribution limitation and a notice that unverified extracted ratings are withheld, and — when available — a plain-English, source-cited summary of how the VA defines and rates the condition. Educational statistics, not a prediction or legal advice.

  Parameters: condition, example_limit?

Try asking

• “How do tinnitus appeals actually turn out at the Board?”
• “I was near burn pits in Iraq — is my condition presumptive under the PACT Act?”
• “What would ratings of 50%, 30%, and 10% combine to?”
• “What are my options after a VA denial, and how do the three lanes differ?”

Fair use & trust

• Read-only: no tool writes anything, and nothing about your users is stored.
• Rate limits: 30 requests/minute per IP, 600/minute global. Please cache on your side.
• The data comes from the public Board of Veterans’ Appeals record, summarized and confidence-gated — see how we build this.
• Results are educational information from public BVA decisions — not legal advice, not a prediction, and not affiliated with or endorsed by the U.S. Department of Veterans Affairs or any government agency. Please surface that framing (and the source links) to your users. Full disclaimer.