MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Data access / search

org.vicp-registry/vicp-registry

Search 13,000+ US vaccine court (VICP) decisions: cases, court text, statistics, attorneys. Free.

Checks passed
11 / 22

3 failed · 8 not measured

Median response
1017 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
10

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
220
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 1017 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name VICP Registry.

  • Pass
    Lists tools

    tools/list returned 10 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 1017 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 1017 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Fail
    Parameters documented

    0 of 36 parameters have a description (0%). The bar is 80%.

  • Fail
    Safety hints

    10 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-07-11T02:29:44.010522Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using org.vicp-registry/vicp-registry

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http org-vicp-registry-vicp-registry https://vicp-registry.org/mcp

Capabilities

Tools 10

fetch

Fetch the full record + source text of one case by its id (package_id). (Deep-research companion to search.)

Discovered
get_attorney

Get one attorney's profile: bio (when available), aggregate outcomes, and their most recent cases. Name is matched case-insensitively.

Discovered
get_case

Get the complete curated record for one case by package_id. Includes the AI-assisted case summary, all extracted fields, attorney and special master, plus links: canonical page, plain-text source bundle, and per-document PDF links where available.

Discovered
get_case_text

Get the staged plain text of a case's public court documents. Long decisions can exceed 100 pages; the text is returned in chunks. Use offset_chars from the previous response's next_offset to page through. max_chars is capped at 50,000.

Discovered
get_filters

List all valid filter values: canonical vaccine names (with case counts), condition categories, outcomes, special masters, and the dataset's date range. Call this before filtering so you use real values instead of guessing.

Discovered
get_special_master

Decision patterns for one special master: outcome breakdown, top vaccines/conditions in their docket, and recent cases.

Discovered
get_statistics

Aggregate statistics over the case corpus, optionally filtered. group_by: vaccine | condition | outcome | year | special_master Returns per-group: total cases, compensated count, compensation rate, death count, and median award among compensated cases (awards over $10M excluded from the median due to a known unit-extraction bug). IMPORTANT framing: these describe the VICP case-record dataset, not vaccine-safety rates in the general population.

Discovered
search

Search VICP vaccine-injury cases by free text. Returns result ids for use with fetch. (Alias of search_cases for deep-research clients; prefer search_cases when structured filters are available.)

Discovered
search_attorneys

Search petitioner attorneys and firms by name. Returns per-attorney aggregate stats: case count, compensation rate, main vaccines, and firm. Useful for 'who has handled X cases' questions.

Discovered
search_cases

Search VICP cases with structured filters. - query: free text matched against petitioner identifier, condition, package id, caption name and the AI case summary. - vaccine: canonical vaccine name (use get_filters() for valid values, e.g. "Influenza (flu)", "DTaP/DPT", "MMR", "COVID-19", "Hepatitis B"). - condition_category / outcome: exact values from get_filters(). - decision_type: how the case was decided (stipulation, proffer, reasoned, reasoned_damages, procedural, unclear). - pediatric_only uses the broad pediatric cohort definition (is_minor OR is_minor_inferred OR age<18) — strict age-only filtering undercounts pediatric cases substantially. - dates are ISO strings (YYYY-MM-DD); awards are USD integers. - sort: decision_date_desc|decision_date_asc|filed_asc|filed_desc|award_desc|award_asc - Returns total match count plus one page of compact case records with canonical URLs. Use get_case(package_id) for the full record.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected1017 ms10