bva-corpus

900,000+ Board of Veterans' Appeals decisions: VA outcomes, grant rates, PACT Act, ratings.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
75%
Naming quality
96%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~3,377Tokens (tool definitions)
~2.4 KBTypical response size
Significant attention impact (2.64% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "bva-corpus": {
      "url": "https://www.veterans-rights.com/api/mcp"
    }
  }
}

Remote endpoints

https://www.veterans-rights.com/api/mcpstreamable-http

What it can do

Tool inventory

Tools (10)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢search_bva_decisions(query, condition, disposition, exposure_basis, service_connection_theory, ...)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 200,
      "description": "English full-text websearch over summaries, reasoning and condition text, as in the public decision library. Not literal substring matching."
    },
    "condition": {
      "type": "string",
      "maxLength": 80,
      "description": "A claimed condition, e.g. \"tinnitus\", \"PTSD\"."
    },
    "disposition": {
      "type": "string",
      "enum": [
        "granted",
        "denied",
        "remanded",
        "dismissed",
        "mixed"
      ]
    },
    "exposure_basis": {
      "type": "string",
      "enum": [
        "burn_pit",
        "agent_orange",
        "camp_lejeune",
        "radiation",
        "gulf_war",
        "none"
      ]
    },
    "service_connection_theory": {
      "type": "string",
      "enum": [
        "direct",
        "secondary",
        "presumptive",
        "aggravation",
        "new_and_material"
      ]
    },
    "is_pact_act": {
      "type": "boolean"
    },
    "date_from": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "date_to": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10
    }
  },
  "required": [],
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢find_similar_appeals(conditions, service_connection_theory, exposure_basis, is_pact_act, sample_limit)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "conditions": {
      "type": "array",
      "minItems": 1,
      "maxItems": 5,
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 80
      },
      "description": "Canonical names, slugs or exact aliases, e.g. [\"PTSD\", \"tinnitus\"]. Matches ANY supplied condition. Use list_conditions to discover valid slugs."
    },
    "service_connection_theory": {
      "type": "string",
      "enum": [
        "direct",
        "secondary",
        "presumptive",
        "aggravation",
        "new_and_material"
      ]
    },
    "exposure_basis": {
      "type": "string",
      "enum": [
        "burn_pit",
        "agent_orange",
        "camp_lejeune",
        "radiation",
        "gulf_war",
        "none"
      ]
    },
    "is_pact_act": {
      "type": "boolean"
    },
    "sample_limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10,
      "default": 5
    }
  },
  "required": [
    "conditions"
  ],
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢check_presumptive_conditions(condition, exposure_basis)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "condition": {
      "type": "string",
      "maxLength": 80,
      "description": "Claimed condition, e.g. \"type 2 diabetes\", \"asthma\"."
    },
    "exposure_basis": {
      "type": "string",
      "enum": [
        "agent_orange",
        "burn_pit",
        "camp_lejeune",
        "radiation",
        "gulf_war"
      ],
      "description": "Known/suspected exposure, if any."
    }
  },
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢explain_appeal_options(decision_stage, eligible_review_context_confirmed, has_new_evidence, wants_hearing)

Explain available review options only after the user confirms the actual decision stage and ordinary modernized-review eligibility. Initial/Supplemental, HLR and final Board decisions have different options; preferences do not establish eligibility. Unknown, legacy, contested, remand-only and pending-review contexts withhold tailored lanes. No personal deadline calculation. Educational only.

Input Schema

{
  "type": "object",
  "properties": {
    "decision_stage": {
      "type": "string",
      "enum": [
        "initial-or-supplemental",
        "higher-level-review",
        "board-final",
        "board-evidence-pending",
        "unknown",
        "board-remand",
        "legacy",
        "contested"
      ],
      "description": "Actual stage explicitly identified by the user from their own notice. Never infer from a denial, hearing preference, or historical decision."
    },
    "eligible_review_context_confirmed": {
      "type": "boolean",
      "description": "True only when the user confirms an ordinary modernized, non-contested issue within the applicable review window, with no pending review, motion or special exception. False or omitted withholds tailored lanes. This does not verify a filing deadline."
    },
    "has_new_evidence": {
      "type": "boolean",
      "description": "Does the veteran have new, relevant evidence to add?"
    },
    "wants_hearing": {
      "type": "boolean",
      "description": "Does the veteran want a hearing before a judge? This never makes a Board appeal available."
    }
  },
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢find_accredited_rep(state, city, rep_type, limit)

Find a VA-accredited representative to help with a disability claim or appeal. Choose an accredited representative: VSO (Veterans Service Organization) representatives — who help FREE — plus accredited claims agents and accredited attorneys. This tool leads with free options first. Returns representatives filtered by state, city and type. Attorneys/agents may generally charge for review after notice of the initial VA decision, subject to fee rules and a written agreement. Not legal advice; not affiliated with the VA.

Input Schema

{
  "type": "object",
  "properties": {
    "state": {
      "type": "string",
      "maxLength": 40,
      "description": "US state (2-letter code or full name)."
    },
    "city": {
      "type": "string",
      "maxLength": 60
    },
    "rep_type": {
      "type": "string",
      "enum": [
        "vso",
        "attorney",
        "claims_agent"
      ]
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10
    }
  },
  "required": [],
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢estimate_combined_rating(ratings)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "ratings": {
      "type": "array",
      "minItems": 1,
      "maxItems": 20,
      "description": "The individual disability ratings to combine.",
      "items": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "percent": {
            "type": "integer",
            "minimum": 0,
            "maximum": 100,
            "description": "Rating percentage 0–100."
          },
          "label": {
            "type": "string",
            "maxLength": 80,
            "description": "Optional name, e.g. \"PTSD\"."
          },
          "bilateral": {
            "type": "boolean",
            "description": "Part of a paired-limb (bilateral) set under § 4.26."
          }
        },
        "required": [
          "percent"
        ]
      }
    }
  },
  "required": [
    "ratings"
  ],
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢get_claim_process(stage)

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 CAVC court deadline. Call with no arguments for an overview of all stages with typical durations; call with a stage number (1-8) for a deep dive on that stage: what to expect, how long it takes, the key tip, and do/don’t guidance. Use this whenever a veteran asks what happens after filing, where they are in the process, what a C&P exam is, or what to do at their current stage. Educational only, not legal advice.

Input Schema

{
  "type": "object",
  "properties": {
    "stage": {
      "type": "integer",
      "minimum": 1,
      "maximum": 8,
      "description": "Stage number 1-8 for a deep dive on one stage. Omit for an overview of all eight stages."
    }
  },
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢get_corpus_stats

Return live statistics about the Veterans’ Rights corpus: the number of vetted Board of Veterans’ Appeals decisions analyzed, the distribution of outcomes (granted / denied / remanded / mixed), the date range the decisions cover, and the number of accredited representatives in the directory. Use this to establish the scale of the data behind an answer, or when someone asks "how much data do you have / how current is it". Counts reflect only quality-filtered, publicly visible decisions.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢list_conditions

List the standardized conditions the Veterans’ Rights corpus organizes Board of Veterans’ Appeals decisions under, each with the number of vetted decisions, grants, and remands (full-corpus counts) and the body-system category. Use this to discover which conditions have data, to get the exact slug for get_condition_report, or to see which conditions occur in this collection. Counts describe whole decisions mentioning each condition, not condition-specific wins or individual chances. Counts reflect only quality-filtered, publicly visible decisions.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}
🟢get_condition_report(condition, example_limit)

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. The richest single call for "tell me about VA claims for <condition>". Educational statistics, not a prediction or legal advice.

Input Schema

{
  "type": "object",
  "properties": {
    "condition": {
      "type": "string",
      "description": "Condition slug (e.g. \"ptsd\", \"sleep-apnea\") or a common name/alias (e.g. \"PTSD\", \"acid reflux\")."
    },
    "example_limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10,
      "default": 4
    }
  },
  "required": [
    "condition"
  ],
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "description": "Tool-specific result payload."
    },
    "link": {
      "type": "string",
      "description": "Tagged deep link into the matching veterans-rights.com page."
    },
    "disclaimer": {
      "type": "string",
      "description": "Standing not-legal-advice / not-VA framing."
    }
  },
  "required": [
    "data",
    "link",
    "disclaimer"
  ],
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded10 tools
verifiedversion not recorded10 tools
verifiedversion not recorded10 tools
verifiedversion not recorded10 tools
verifiedversion not recorded10 tools
verifiedversion not recorded10 tools