com.veterans-rights/bva-corpus
REMOTE · WWW.VETERANS-RIGHTS.COM
VA disability claims and appeals, grounded in Board of Veterans' Appeals decisions.
Available components
Last scanned (19 hours ago)
Scores higher than 91% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Health and Science
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 Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability78
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2075 tokens (~172/item across 12 items; 10 tools + 2 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 Coverage85
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 46% 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
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 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
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 →
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.
- 20 Nov 26 0
- Tool “find_similar_appeals” rewrote its description, which is the text the model reads security
- “find_similar_appeals” reworded the description of “conditions” cosmetic
- 14 Nov 26 +2
- The server rewrote its instructions, which are the text every model session reads security
- Tool “explain_appeal_options” rewrote its description, which is the text the model reads security
- Tool “find_accredited_rep” rewrote its description, which is the text the model reads security
- Tool “get_claim_process” rewrote its description, which is the text the model reads security
- Tool “get_condition_report” rewrote its description, which is the text the model reads security
- Tool “get_corpus_stats” rewrote its description, which is the text the model reads security
- Tool “list_conditions” rewrote its description, which is the text the model reads security
- MCP protocol: fail → pass ▲ functional
- MCP protocol version: 2025-06-18 → 2025-11-25 functional
- Server version: 1.1.0 → 1.2.0 functional
- “explain_appeal_options” reworded the description of “decision_stage” cosmetic
- “explain_appeal_options” reworded the description of “eligible_review_context_confirmed” cosmetic
- “explain_appeal_options” reworded the description of “has_new_evidence” cosmetic
- “explain_appeal_options” reworded the description of “wants_hearing” cosmetic
- “find_similar_appeals” reworded the description of “conditions” cosmetic
- 11 Nov 26 0
- Stability: 0.97 → pass security
- Schema quality: excellent → good functional
- “get_condition_report” reworded the description of “condition” cosmetic
- 10 Nov 26 0
- 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
- 22 Oct 26 0
- Stability: fail → pass ▲ security
- 10 Oct 26 0
- Tool “search_bva_decisions” rewrote its description, which is the text the model reads security
- “search_bva_decisions” reworded the description of “query” cosmetic
- 28 Sept 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
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://www.veterans-rights.com/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=www.veterans-rights.com | CN=YR2,O=Let's Encrypt,C=US | 10 Oct 2026 | 8 Jan 2027 | RSA 2048 | SHA256-RSA | 55fb2ad1816fb908c01309cf170d51610eb |
| SANs: www.veterans-rights.com | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.veterans-rights.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| veterans-rights.com. | 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=63072000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; base-uri 'self'; object-src 'none'; frame-ancestors 'none'; form-action 'self'; script-src 'self' 'unsafe-inline' https://www.googletagmanager.com https://www.google-analytics.com; style-src 'self' 'unsafe-inline'; img-src 'self' data: https://www.googletagmanager.com https://www.google-analytics.com; font-src 'self'; connect-src 'self' https://www.googletagmanager.com https://www.google-analytics.com https://*.google-analytics.com https://eiowlqpeylpxwgjmhizc.supabase.co wss://eiowlqpeylpxwgjmhizc.supabase.co; frame-src 'self'; upgrade-insecure-requests |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.veterans-rights.com/api/mcp | Verified | 200 | |
| http (plaintext) | http://www.veterans-rights.com/api/mcp | HTTPS enforced | 308 | https://www.veterans-rights.com/api/mcp |
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 →
check_presumptive_conditions Check presumptive conditions ~155
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.
| Name | Type | Req | Description |
|---|---|---|---|
| condition | string | – | Claimed condition, e.g. "type 2 diabetes", "asthma". |
| exposure_basis | string | – | Known/suspected exposure, if any. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
estimate_combined_rating Estimate combined rating ~132
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.
| Name | Type | Req | Description |
|---|---|---|---|
| ratings | array | yes | The individual disability ratings to combine. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
explain_appeal_options Explain appeal options ~252
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.
| Name | Type | Req | Description |
|---|---|---|---|
| decision_stage | string | – | The decision stage stated on the user’s own VA notice. A denial, a hearing preference or a historical decision does not establish the stage; "unknown" returns general information. |
| eligible_review_context_confirmed | boolean | – | True when the user has confirmed an ordinary modernized, non-contested issue within the applicable review window, with no pending review, motion or special exception. False or omitted returns general… |
| has_new_evidence | boolean | – | Whether the veteran has new, relevant evidence to add. |
| wants_hearing | boolean | – | Whether the veteran wants a hearing before a Veterans Law Judge. A hearing preference does not make a Board appeal available. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
find_accredited_rep Find an accredited representative ~124
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.
| Name | Type | Req | Description |
|---|---|---|---|
| city | string | – | – |
| limit | integer | – | – |
| rep_type | string | – | – |
| state | string | – | US state (2-letter code or full name). |
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
find_similar_appeals Find similar appeals ~165
Find source-linked recent Board decisions by condition name, slug, alias or common wording. Inspects up to the 50 most recent indexed decisions per condition. A phrase like "sleep apnea secondary to PTSD" looks for decisions in both recent lists with a decision-level secondary theory. The direction of the relationship requires verification in the original decision. Results are bounded research examples. Grant rates are withheld.
| Name | Type | Req | Description |
|---|---|---|---|
| conditions | array | yes | Matches any supplied entry. Examples include "knee pain", "PTSD" and "sleep apnea secondary to PTSD". Use up to five distinct conditions in total. |
| exposure_basis | string | – | – |
| is_pact_act | boolean | – | – |
| sample_limit | integer | – | – |
| service_connection_theory | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
get_claim_process VA claim process guide ~170
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.
| Name | Type | Req | Description |
|---|---|---|---|
| stage | integer | – | Stage number 1-8 for a deep dive on one stage. Omit for an overview of all eight stages. |
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
get_condition_report Condition report ~188
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.
| Name | Type | Req | Description |
|---|---|---|---|
| condition | string | yes | Nonempty condition slug (e.g. "ptsd", "sleep-apnea") or common name/alias (e.g. "PTSD", "acid reflux"), without control characters. |
| example_limit | integer | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
get_corpus_stats Corpus statistics ~87
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.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
list_conditions List conditions ~75
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.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
search_bva_decisions Search BVA decisions ~216
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.
| Name | Type | Req | Description |
|---|---|---|---|
| condition | string | – | A claimed condition, e.g. "tinnitus", "PTSD". |
| date_from | string | – | – |
| date_to | string | – | – |
| disposition | string | – | – |
| exposure_basis | string | – | – |
| is_pact_act | boolean | – | – |
| limit | integer | – | – |
| query | string | – | English full-text websearch over summaries, reasoning and condition text, as in the public decision library. Not literal substring matching. |
| service_connection_theory | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | yes | Tool-specific result payload. |
| disclaimer | string | yes | Standing not-legal-advice / not-VA framing. |
| link | string | yes | Tagged deep link into the matching veterans-rights.com page. |
No examples provided.
How do I install the com.veterans-rights/bva-corpus MCP server?
com.veterans-rights/bva-corpus is a hosted endpoint at https://www.veterans-rights.com/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 · www.veterans-rights.com
claude mcp add --transport http com-veterans-rights-bva-corpus 'https://www.veterans-rights.com/api/mcp'
What is the com.veterans-rights/bva-corpus MCP server?
com.veterans-rights/bva-corpus is an MCP server listed in the public MCP registry as com.veterans-rights/bva-corpus. VA disability claims and appeals, grounded in Board of Veterans' Appeals decisions. This page covers its hosted endpoint (https://www.veterans-rights.com/api/mcp).
Is the com.veterans-rights/bva-corpus MCP server safe to use?
com.veterans-rights/bva-corpus scores 87 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 com.veterans-rights/bva-corpus MCP server expose?
com.veterans-rights/bva-corpus exposes 10 tools: search_bva_decisions, find_similar_appeals, check_presumptive_conditions, explain_appeal_options, find_accredited_rep, and 5 more. Their descriptions and schemas cost roughly 1,564 tokens of context every time the server is loaded.
Does the com.veterans-rights/bva-corpus MCP server require authentication?
No. We connected to com.veterans-rights/bva-corpus without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the com.veterans-rights/bva-corpus MCP server still maintained?
com.veterans-rights/bva-corpus 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 com.veterans-rights/bva-corpus MCP server?
VerifyMCP ran 13 checks on com.veterans-rights/bva-corpus, 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.