# ImOnFHIR (remote · imonfhir.com)

imonfhir.com tools: HL7 digest, Jira status, PAS validation, IG and payload compare, rule evidence.

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `imonfhir.com`: 74/100 (this document), [markdown](https://verifymcp.io/servers/com-imonfhir-site/api-v1-mcp.md), [page](https://verifymcp.io/servers/com-imonfhir-site/api-v1-mcp)

## Channel facts

- Endpoint: `https://imonfhir.com/api/v1/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

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. 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.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - 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.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1686 tokens (~210/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 88% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the ImOnFHIR MCP server?

ImOnFHIR is a hosted endpoint at https://imonfhir.com/api/v1/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.

### Claude

```bash
claude mcp add --transport http com-imonfhir-site 'https://imonfhir.com/api/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-imonfhir-site": {
      "url": "https://imonfhir.com/api/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-imonfhir-site": {
      "type": "http",
      "url": "https://imonfhir.com/api/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-imonfhir-site]
url = "https://imonfhir.com/api/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-imonfhir-site": {
      "type": "remote",
      "url": "https://imonfhir.com/api/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-imonfhir-site --url 'https://imonfhir.com/api/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-imonfhir-site:
    url: "https://imonfhir.com/api/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-imonfhir-site": {
      "Transport": "http",
      "Url": "https://imonfhir.com/api/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-imonfhir-site -t streamable-http -u 'https://imonfhir.com/api/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-imonfhir-site": {
      "type": "http",
      "url": "https://imonfhir.com/api/v1/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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 74, +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.

### 2026-11-18 (score 73, +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.

### 2026-11-16 (score 72, 0)

- [security] Tool “validate_bundle” rewrote its description, which is the text the model reads

### 2026-11-15 (score 72, +1)

- [security] Tool “validate_bundle” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 185 → 206
- [functional] New tool “get_validation_findings”

### 2026-11-14 (score 71, 0)

- [security] Tool “compare_igs” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03

### 2026-11-13 (score 71)

First indexed and scored.

## MCP tools (8)

### `search_digest` (~123 tokens)

Search the standards digest

Search the public digest of HL7 standards discussions. Returns at most 20 items, each with every claim's evidence record and canonical_url — no summary text. Use get_digest_item for one item in full.

Input parameters:

- `q` (string): Words to match in the title, work group or HL7 Jira keys.
- `since` (string): ISO date; only items with activity on or after it.
- `workgroup` (string): A work group (the feed's list slug, e.g. "da-vinci-pas"). An unknown one is an error.

Output parameters:

- `attribution` (string)
- `count` (integer)
- `items` (array)

### `get_digest_item` (~57 tokens)

Read one digest item

One digest item in full: each claim (question, outcome, impact, stage, next step) with its own evidence record, plus HL7 Jira statuses and canonical_url.

Input parameters:

- `id` (string, required): The item id from search_digest.

Output parameters:

- `attribution` (string)
- `canonical_url` (string)
- `claims` (array)
- `id` (string)
- `jira` (array)
- `last_activity` (string|null)
- `source_url` (string|null)
- `stage` (string|null)
- `stage_evidence` (object|null)
- `standards` (array)
- `title` (string|null)
- `workgroup` (string|null)

### `get_jira_status` (~71 tokens)

HL7 Jira status

Up to 50 HL7 Jira keys: status, resolved, resolution, last_verified with its jira_verified evidence record, lifecycle stage, source_url (HL7 Jira) and the canonical_url of public items that cite it. "applied" is not "published".

Input parameters:

- `keys` (array, required)

Output parameters:

- `attribution` (string)
- `statuses` (array)

### `validate_bundle` (~278 tokens)

Validate a PAS bundle

Validate a synthetic Da Vinci PAS Submit Bundle with the ImOnFHIR validator. Synthetic payloads only. Never send real patient data. Findings describe a synthetic Bundle. Body cap 2 MB, 10 calls per minute. Over MCP every answer carries `verdict`: the validator's own readiness verdict, the one its Lab shows (readiness, a one-sentence statement, its readiness dimensions and its consolidated counts); read it first. Then `summary`: false means the whole OperationOutcome is in `outcome`; true means it was over 100,000 characters, so the answer is a bounded summary instead (the coverage note; distinct problems by severity, a problem the validator's layers report twice counted once, with the raw counts beside them; counts by issue code, rule family and resource; the PAS profile versions the issues cite; the 25 most serious kinds of finding, and how many were not listed). A summary's findings (never the bundle) are kept 1 hour: get_validation_findings pages every issue with the result_id it gives. POST /api/v1/validate returns the whole OperationOutcome.

Input parameters:

- `bundle` (object, required): A FHIR Bundle (resourceType "Bundle"). Synthetic only.
- `ig` (string)
- `version` (string): A PAS version the validator allows; omitted, the default.

Output parameters:

- `counts` (object)
- `coverage` (object)
- `expires_at` (string|null)
- `findings_digest` (string|null)
- `findings_listed` (integer)
- `findings_omitted` (integer)
- `full_report` (object)
- `ig`
- `instruction_block` (object)
- `key_findings` (array)
- `next_steps` (array)
- `notice` (string)
- `outcome` (object): Present only when summary is false.
- `pas_profile_versions_cited` (array)
- `requestId` (string)
- `result_id` (string|null): The id get_validation_findings reads; null when the result could not be kept (see store_note).
- `store_note` (string|null)
- `summary` (boolean): false: the whole OperationOutcome is in outcome. true: it was too long to send whole; this is a bounded summary.
- `summary_notice` (string)
- `truncated` (boolean)
- `verdict` (object): The validator product's own readiness verdict, the one its Lab shows; read verdict.statement first.
- `version` (string|null)
- `version_note` (string|null)

### `get_validation_findings` (~206 tokens)

Every finding of a large validation

Every issue of one large validate_bundle result, a page at a time. Give it the result_id from a validate_bundle summary; it reads what validate_bundle kept (the findings, never the bundle) for 1 hour, so the bundle is not sent again and the validator does not run again. The issues come in the order POST /api/v1/validate returns them; call again with page.next_offset until it is null. Optional severity filters to fatal, error, warning or information. An unknown or expired result_id is an error: run validate_bundle again. Synthetic payloads only. Never send real patient data. Findings describe a synthetic Bundle. 60 calls per minute; MCP only.

Input parameters:

- `offset` (integer): Where the page starts, counting the issues chosen (default 0); use page.next_offset.
- `result_id` (string, required): From a validate_bundle summary (result_id or next_steps).
- `severity` (string): Only issues of this severity.

Output parameters:

- `clipped` (array)
- `expires_at` (string)
- `findings_digest` (string)
- `issues` (array)
- `next_steps` (array)
- `notice` (string)
- `page` (object)
- `pas_version` (string|null)
- `result_id` (string)
- `severity` (string|null)

### `compare_igs` (~166 tokens)

Compare two IGs

Compare two implementation guides, each "packageId#version": one guide at two versions (version diff) or two guides (stack compare). Over MCP the answer is a bounded summary (the risk level and, in plain words, the rule that set it; counts per change type, a change-type by impact breakdown, the profiles carrying the most breaking changes, what moved in value set definitions, the most serious findings, and where the whole report is); POST /api/v1/compare returns the whole report.

Input parameters:

- `ig_a` (string, required): e.g. "hl7.fhir.us.davinci-pas#2.0.1"
- `ig_b` (string, required): e.g. "hl7.fhir.us.davinci-pas#2.1.0"

Output parameters:

- `breakdown` (object)
- `comparison_notes` (array)
- `comparison_status` (string|null)
- `counts` (object)
- `findings_listed` (integer)
- `findings_omitted` (integer)
- `full_report` (object)
- `ig_a` (string)
- `ig_b` (string)
- `mode`
- `notice` (string)
- `risk` (object|null)
- `summary`
- `top_findings` (array)
- `top_profiles` (object)
- `truncated` (boolean)
- `valueset_definition_changes` (array)
- `valueset_unchanged_unlisted` (integer)

### `compare_payloads` (~176 tokens)

Compare two payloads

Compare two synthetic FHIR payloads (a resource or a Bundle each, 1 MB at most per side) and report where they differ: which rows are missing or extra, which field paths changed, and counts. It returns no field values; it lists up to 200 rows and 300 field paths (the paths come from the key names in the payloads) and counts the rest. Synthetic data only. The payloads are sent to imonfhir.com for the call and the site does not store them; the browser Compare tool at /lab/compare keeps them on your machine.

Input parameters:

- `a` (object|string, required): A FHIR resource or Bundle (a JSON object, or a string holding one). Synthetic only.
- `b` (object|string, required): The payload to compare it with, in the same form.

Output parameters:

- `identical` (boolean)
- `notice` (string)
- `paths_listed` (integer)
- `paths_omitted` (integer)
- `rows` (array)
- `rows_listed` (integer)
- `rows_omitted` (integer)
- `stats` (object)
- `truncated` (boolean)

### `explain_finding` (~367 tokens)

Evidence for a rule or a requirement

The evidence behind a semantic validator rule, not an explanation of it. Give rule_id (a rule id such as PAS-SEM-PROV-001) and get the rule's id, version, title, description, source, category and default severity as the validator states them, plus, only when the rule's explanation entry declares anchors that all resolve, the HL7 statements for them: package, version, key, conformance word, HL7's statement text verbatim (its markdown) and the sha256 of that text. It abstains, with the reason, when no anchor is committed or one does not resolve. 0 of 17 rule explanations have committed anchors; a rule id abstains until its anchors are committed. Or give requirement ({packageId, version, key}) and get that one HL7 statement the same way. An unknown package, version or key is an error, and so is a package version that has a catalog but no committed statement text. Statement text is committed for hl7.fhir.us.davinci-pas@2.2.1; a package version that has a catalog but no committed text is an error. It also returns an instruction block telling your assistant how to use the evidence. It calls nothing outside this site. Prose your assistant writes around the passages is not controlled by ImOnFHIR.

Input parameters:

- `requirement` (object): One HL7 statement: its package id, version and statement key, e.g. hl7.fhir.us.davinci-pas, 2.2.1, ainfo-3. Give this or rule_id, not both.
- `rule_id` (string): A semantic rule id, e.g. PAS-SEM-PROV-001. Give this or requirement, not both.

Output parameters:

- `abstain` (object)
- `instruction_block` (object)
- `mode`
- `notice` (string)
- `outcome`
- `passages` (array)
- `rule` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-imonfhir-site/api-v1-mcp#diagnostics

## Score history

- 2026-11-21: 74
- 2026-11-20: 74
- 2026-11-19: 73
- 2026-11-18: 73
- 2026-11-17: 72
- 2026-11-16: 72
- 2026-11-15: 72
- 2026-11-14: 71
- 2026-11-13: 71

## Common questions

### What is the ImOnFHIR MCP server?

ImOnFHIR is an MCP server listed in the public MCP registry as com.imonfhir/site. imonfhir.com tools: HL7 digest, Jira status, PAS validation, IG and payload compare, rule evidence. This page covers its hosted endpoint (https://imonfhir.com/api/v1/mcp).

### Is the ImOnFHIR MCP server safe to use?

ImOnFHIR scores 74 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 ImOnFHIR MCP server expose?

ImOnFHIR exposes 8 tools: search_digest, get_digest_item, get_jira_status, validate_bundle, get_validation_findings, and 3 more. Their descriptions and schemas cost roughly 1,444 tokens of context every time the server is loaded.

### Does the ImOnFHIR MCP server require authentication?

No. We connected to ImOnFHIR without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ImOnFHIR MCP server still maintained?

ImOnFHIR 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 ImOnFHIR MCP server?

VerifyMCP ran 13 checks on ImOnFHIR, 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.

## Links

- Remote endpoint: https://imonfhir.com/api/v1/mcp
- Website: https://imonfhir.com/agents
- Changelog RSS feed: https://verifymcp.io/servers/com-imonfhir-site/api-v1-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-imonfhir-site/api-v1-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-imonfhir-site/api-v1-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-imonfhir-site/api-v1-mcp
