# Forever Healthy Evidence MCP (npm · evidence-mcp)

Power tools for AI agents to improve and speed up medical literature research

- Trust score: 66/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `evidence-mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/forever-healthy-evidence-mcp/evidence-mcp.md), [page](https://verifymcp.io/servers/forever-healthy-evidence-mcp/evidence-mcp)

## Channel facts

- Registry: `npm`
- Package: `evidence-mcp`
- Version: `1.0.17`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 32 of 107 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 5067 tokens (~422/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Forever Healthy Evidence MCP server?

Forever Healthy Evidence MCP runs locally as an npm package, launched with npx -y evidence-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add forever-healthy-evidence-mcp -- npx -y evidence-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "forever-healthy-evidence-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "evidence-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "forever-healthy-evidence-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "evidence-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add forever-healthy-evidence-mcp -- npx -y evidence-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "forever-healthy-evidence-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "evidence-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add forever-healthy-evidence-mcp --command npx --arg -y --arg evidence-mcp
```

### Hermes

```yaml
mcp_servers:
  forever-healthy-evidence-mcp:
    command: "npx"
    args: ["-y", "evidence-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "forever-healthy-evidence-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "evidence-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add forever-healthy-evidence-mcp -t stdio -c npx -a -y evidence-mcp
```

### Other

```json
{
  "mcpServers": {
    "forever-healthy-evidence-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "evidence-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 64, 0)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.17 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 1.0.0 → 1.0.17

### 2026-11-16 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 63, +20)

- [security regression] Known CVEs: unverified → fail
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Dependency health: unverified → 0.88

### 2026-11-14 (score 43, +1)

- [security regression] Known CVEs: fail → unverified
- [security improvement] Malware scan: unverified → pass
- [security improvement] Source repository: fail → pass
- [functional regression] Security disclosure: unverified → fail
- [functional regression] Dependency health: 0.88 → unverified
- [functional] Package version: 0.2.46 → 1.0.0
- [functional] Package version: 0.2.46 → 0.2.47

### 2026-11-13 (score 42, 0)

- [security regression] Stability: 0.03 → unverified
- [security regression] Tool safety: pass → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.2.43 → 0.2.46
- [functional] Package version: 0.2.43 → 0.2.44

### 2026-11-12 (score 42, +6)

- [security regression] CVE-2023-54404 affects this package: high
- [security regression] Known CVEs: unverified → fail
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Dependency health: unverified → 0.88
- [functional] Package version: 0.2.42 → 0.2.43

## MCP tools (12)

### `fh_library_add` (~256 tokens)

Download and store one record — a paper (pmid:, doi:), a drug label (dailymed:<set ID>) or a trial record (nct:<8 digits>) — and return its status JSON. A paper gets its record, abstract and correction notices from PubMed (Crossref for a DOI PubMed does not index), then the full text from the configured sources; a label or trial record is stored as a full text. A stored full text is returned without any download; an abstract-level record retries only sources that failed transiently; a record older than 30 days gets its notices re-read.

Input parameters:

- `id` (string, required): ID as "type:value": a paper "pmid:30955454" (bare digits count as pmid) or "doi:10.5812/asjsm.110753" (a paper PubMed does not index; a DOI PubMed indexes is taken as its PMID), a drug label "dailyme…

### `fh_library_status` (~177 tokens)

Read-only status of the library entry for one ID — a paper, a drug label or a trial record: the same status JSON as fh_library_add, or level "missing" when there is no entry. Never fetches.

Input parameters:

- `id` (string, required): ID as "type:value": a paper "pmid:30955454" (bare digits count as pmid) or "doi:10.5812/asjsm.110753" (a paper PubMed does not index; a DOI PubMed indexes is taken as its PMID), a drug label "dailyme…

### `fh_library_read` (~387 tokens)

One piece of a stored document's Markdown, never the whole. No section/query: the outline (headings with word counts; full text or abstract only). section: that heading's own text (case-insensitive substring; a repeated heading as "Participants [3/12]"), capped at max_chars, its subsections listed. query: passages holding every term, each a window of at most 1000 chars with its section, best first, at most max_hits (more: how many further passages match); partial: true with missing_terms when no passage holds them all. section and query together: inside that section. A missing paper is added first (added: true).

Input parameters:

- `id` (string, required): ID as "type:value": a paper "pmid:30955454" (bare digits count as pmid) or "doi:10.5812/asjsm.110753" (a paper PubMed does not index; a DOI PubMed indexes is taken as its PMID), a drug label "dailyme…
- `max_chars` (integer): Cap for section text (default 6000); passages are capped at 1000 chars each regardless.
- `max_hits` (integer): Cap for query passages (default 5).
- `query` (string): Two or three distinctive terms the paper itself would use — a measure and a unit, an outcome and a group, a compound name — not the claim. Passages holding all of them are returned, else the best par…
- `section` (string): Heading from the outline (case-insensitive substring).

### `fh_verify_claim` (~378 tokens)

Does one source state one finding of a review? claim: the finding as a complete statement (subject, intervention, outcome, number), without citations or the review's framing, and only what this source reports. id: one source the review cites for it — paper, drug label (dailymed:…) or trial record (nct:…); added first when missing. The server reads the stored text and asks a decision model; nothing enters your context. verdict: pass (score is the probability) | fail (the full text does not state it; or only the title is stored — reason says so) | unverifiable (only the abstract is stored and does not state it — reason says so) | error (claim refused: under four words, a fragment, carrying citations; add failed; no model; model failure). basis: full_text | abstract | title. glyphs_unresolved: symbols the PDF font lost; above 0 a failed number may be the font. superseded: true when a stored correction replaced the claim's figure.

Input parameters:

- `claim` (string, required): One finding as a complete statement (subject, intervention, outcome, number), built from the review's words, without its citations and framing.
- `id` (string, required): ID as "type:value": a paper "pmid:30955454" (bare digits count as pmid) or "doi:10.5812/asjsm.110753" (a paper PubMed does not index; a DOI PubMed indexes is taken as its PMID), a drug label "dailyme…

### `fh_info` (~241 tokens)

The server and the whole library as JSON: this server's package name and version (which build is loaded), its log file; evidence directory (evidence_dir) and host; entry count and size on disk; per type (pmid, doi, dailymed, nct) the entries by level (full_text, abstract, title) and retractions; counts of retracted and not-citable entries and of errata, expressions of concern and updates; the retrieval sources in run order and which are off (tiers); the multi-stage download (download): the Playwright servers with the version they must run, the Chrome stages, whether an unlocker is configured; the configuration and where each value came from — environment, .env or default, never the value (config); the decision model behind fh_verify_claim and whether it answers right now (verify); the unlockers and whether each answers right now (unlockers); our own stage hosts — fetch proxy, Playwright servers, Chrome — and whether each is reachable right now (stages); this server's cache hits and misses for fh_verify_claim and fh_fetch_url since it started (cache).

### `fh_fetch_url` (~257 tokens)

Fetch a web page as Markdown: the standard fetch tool, cached and hardened. Use it for any URL instead of a plain fetch or a browser. A page fetched in the last 30 days is answered from disk in milliseconds; a page a plain fetch cannot get (403, rate limit, bot wall, script-rendered) is fetched through the configured browsers and unlockers in this one call. PDFs come back as Markdown; XML, JSON and other text as is. To verify a link, title_only returns just its title line. A PubMed, ClinicalTrials.gov, DailyMed or doi.org URL is answered from the library's record of it.

Input parameters:

- `max_length` (integer): Maximum number of characters to return (default 5000).
- `raw` (boolean): Get the actual HTML content of the requested page, without simplification.
- `start_index` (integer): On return output starting at this character index, useful if a previous fetch was truncated and more context is required.
- `title_only` (boolean): Return only the page's title line. The whole page is still fetched and stored; use this to verify that a link resolves and what it points to.
- `url` (string, required): URL to fetch

### `fh_pubmed_fetch_articles` (~130 tokens)

Title, first author, year, publication types, retracted and library level for up to 200 PubMed IDs in one call. Faster and far smaller than asking PubMed: known papers come from disk, the rest in one request, stored for every later call; rows as arrays in columns order, ~120 characters a paper. Level "not found": PubMed has no such record. For abstract or full text: fh_library_read.

Input parameters:

- `pmids` (array, required): PubMed IDs, "30955454" or "pmid:30955454", up to 200.

### `fh_pubmed_search_articles` (~237 tokens)

Search PubMed with its own query syntax (AND / OR, field tags like [pt], [ti], [mesh]); sort relevance | newest; years "2020-2026". Faster and far smaller than asking PubMed: the total and up to 100 rows as arrays in columns order — PMID, title, first author, year, journal, publication types, PMCID when free full text exists, and the library level when the paper is already stored. The same search is answered from disk for 7 days. For a batch of PMIDs: fh_pubmed_fetch_articles; for abstract or full text: fh_library_read.

Input parameters:

- `max_results` (integer): Rows to return (1–100).
- `query` (string, required): PubMed query, full syntax: "tadalafil AND (systematic review[pt] OR meta-analysis[pt])".
- `sort` (string): relevance (PubMed's ranking) or newest (publication date, latest first).
- `years` (string): Publication years: "2020-2026", "2022-", "-2019" or "2022".

### `fh_clinicaltrials_search_studies` (~281 tokens)

Search ClinicalTrials.gov by free text, intervention or condition; status ongoing | completed | all; sort relevance | newest | largest | completion. Returns the total and up to 100 rows as arrays in columns order: NCT ID, title, status, phase, enrollment ("~100" estimated), start, primary completion, primary outcome, conditions, interventions, has_results. Link: https://clinicaltrials.gov/study/<NCT ID>. Cached 7 days. One trial in detail: fh_clinicaltrials_get_study_record.

Input parameters:

- `condition` (string): Condition or disease, e.g. "hypertension", "type 2 diabetes".
- `intervention` (string): Intervention or treatment, e.g. "tadalafil", "cognitive behavioral therapy".
- `max_results` (integer): Rows to return (1–100).
- `query` (string): Free-text search across all fields (title, conditions, interventions, summary, …); AND / OR / NOT allowed.
- `sort` (string): relevance (the registry's ranking), newest (last update first), largest (enrollment first), completion (completion date, latest first).
- `status` (string): ongoing: recruiting, not yet recruiting, active not recruiting, enrolling by invitation. completed: completed. all: no filter.

### `fh_dailymed_search_labels` (~239 tokens)

Find FDA drug labels on DailyMed by drug name, generic or brand: the total and up to 100 rows as arrays in columns order — set ID, title (drug and form), labeler (the company), published date, version, and the library level when the label is already stored. Newest first. A generic name lists every maker's label; labeler narrows to one company ("Boehringer" for Micardis's maker), a brand name to its own labels. Pass the set ID as "dailymed:<set ID>" to fh_library_read or fh_library_add. Use this, not DailyMed's search page: fetched as Markdown the page shows no set IDs, raw it is some 150,000 characters. The same search is answered from disk for 7 days.

Input parameters:

- `drug_name` (string, required): Generic or brand name: "telmisartan", "Micardis".
- `labeler` (string): Part of the company's name, to narrow to its labels: "Boehringer".
- `max_results` (integer): Rows to return (1–100).

### `fh_clinicaltrials_get_study_record` (~126 tokens)

One ClinicalTrials.gov trial as a review needs it: titles, status and why stopped, phase, design, enrollment, dates, sponsor, conditions, interventions, primary outcomes, eligibility, sites, result publications as pmid: IDs, has_results, brief summary. From the stored record; a missing trial is added first. The whole record: fh_library_read("nct:…").

Input parameters:

- `nct` (string, required): The NCT ID: "nct:05173896", "NCT05173896" or the eight digits.

### `fh_clinicaltrials_get_study_results` (~142 tokens)

The posted results of one ClinicalTrials.gov trial — participant flow, baseline, every outcome measure as a table, adverse events — as Markdown from the stored record, capped at max_chars, outcome titles listed; fh_library_read("nct:…", section: <title>) returns one measure whole. has_results false when the registry holds none. A missing trial is added first.

Input parameters:

- `max_chars` (integer): Cap for the results text (default 6000).
- `nct` (string, required): The NCT ID: "nct:05173896", "NCT05173896" or the eight digits.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/forever-healthy-evidence-mcp/evidence-mcp#diagnostics

## Score history

- 2026-11-21: 66
- 2026-11-20: 66
- 2026-11-19: 65
- 2026-11-18: 65
- 2026-11-17: 64
- 2026-11-16: 64
- 2026-11-15: 63
- 2026-11-14: 43
- 2026-11-13: 42
- 2026-11-12: 42
- 2026-11-11: 36

## Common questions

### What is the Forever Healthy Evidence MCP server?

Forever Healthy Evidence MCP is listed in the public MCP registry as io.github.forever-healthy/evidence-mcp. Power tools for AI agents to improve and speed up medical literature research. This page covers its npm package (evidence-mcp).

### Is the Forever Healthy Evidence MCP server safe to use?

Forever Healthy Evidence MCP scores 66 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. 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 Forever Healthy Evidence MCP server expose?

Forever Healthy Evidence MCP exposes 12 tools: fh_library_add, fh_library_status, fh_library_read, fh_verify_claim, fh_info, and 7 more. Their descriptions and schemas cost roughly 2,851 tokens of context every time the server is loaded.

### Is the Forever Healthy Evidence MCP server still maintained?

Forever Healthy Evidence MCP 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 licence is the Forever Healthy Evidence MCP server under?

Forever Healthy Evidence MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Forever Healthy Evidence MCP server?

VerifyMCP ran 16 checks on Forever Healthy Evidence MCP, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/evidence-mcp
- Socket report: https://socket.dev/npm/package/evidence-mcp
- Repository: https://github.com/forever-healthy/evidence-mcp
- Changelog RSS feed: https://verifymcp.io/servers/forever-healthy-evidence-mcp/evidence-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/forever-healthy-evidence-mcp/evidence-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/forever-healthy-evidence-mcp/evidence-mcp.json
- HTML version of this page: https://verifymcp.io/servers/forever-healthy-evidence-mcp/evidence-mcp
