# Plan Data API (remote · api.form5500data.com)

Form 5500 data for prospecting and research: U.S. retirement plans, recordkeepers, fees, switches.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.form5500data.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-form5500data-plan-data/api.md), [page](https://verifymcp.io/servers/com-form5500data-plan-data/api)

## Channel facts

- Endpoint: `https://api.form5500data.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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**: 74/100
  - 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 57/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3731 tokens (~466/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**: 40/100
  - Stability observed for 12 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 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 supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Plan Data API MCP server?

Plan Data API is a hosted endpoint at https://api.form5500data.com/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-form5500data-plan-data 'https://api.form5500data.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-form5500data-plan-data": {
      "url": "https://api.form5500data.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-form5500data-plan-data": {
      "type": "http",
      "url": "https://api.form5500data.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-form5500data-plan-data]
url = "https://api.form5500data.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-form5500data-plan-data": {
      "type": "remote",
      "url": "https://api.form5500data.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-form5500data-plan-data --url 'https://api.form5500data.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-form5500data-plan-data:
    url: "https://api.form5500data.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-form5500data-plan-data": {
      "Transport": "http",
      "Url": "https://api.form5500data.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-form5500data-plan-data -t streamable-http -u 'https://api.form5500data.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-form5500data-plan-data": {
      "type": "http",
      "url": "https://api.form5500data.com/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 73, +1)

- [security] Tool “get_plan_fees” rewrote its description, which is the text the model reads
- [cosmetic] “search_plans” reworded the description of “name”

### 2026-11-17 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 70, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_plan_changes” rewrote its description, which is the text the model reads
- [security] Tool “get_plan” rewrote its description, which is the text the model reads
- [security] Tool “get_plan_fees” rewrote its description, which is the text the model reads
- [security] Tool “get_plan_history” rewrote its description, which is the text the model reads
- [security] Tool “list_prospects” rewrote its description, which is the text the model reads
- [security] Tool “search_plans” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 3311 → 3736
- [functional] New tool “get_account”
- [cosmetic] “find_plan_changes” reworded the description of “event_type”
- [cosmetic] “find_plan_changes” reworded the description of “from_recordkeeper”
- [cosmetic] “find_plan_changes” reworded the description of “recordkeeper”
- [cosmetic] “find_plan_changes” reworded the description of “to_recordkeeper”

### 2026-11-11 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_plan_changes” rewrote its description, which is the text the model reads
- [security] Tool “get_plan” rewrote its description, which is the text the model reads
- [security] Tool “get_plan_fees” rewrote its description, which is the text the model reads
- [security] Tool “get_plan_history” rewrote its description, which is the text the model reads
- [security] Tool “list_prospects” rewrote its description, which is the text the model reads
- [security] Tool “search_plans” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03

### 2026-11-09 (score 68)

First indexed and scored.

## MCP tools (8)

### `search_plans` (~587 tokens)

Find plans by company name, EIN, state, size, recordkeeper or plan type

Find plans. Give at least one of `name`, `ein`, `state` or `recordkeeper`; the other filters narrow
the list. Each result is a short summary: call `get_plan` with its `ein` and `pn` for the profile.

With `name`, results are ordered by match score, then size; without it, largest plans first. Plans
that ended are hidden unless `include_ended=true`. Paging stops at offset 500: narrow the filters to
see more.

Price: $0.01 per call, paid in USDC on Base (mainnet) with x402 (MCP transport), or from card credits (an app signed in at /connect, or an 'Authorization: Bearer <key>' header). Without payment the tool returns the payment requirements. Errors and empty results aren't charged.

Same data as GET /search of the Plan Data API.

Input parameters:

- `ein`: Sponsor EIN (9 digits, dashes allowed). Lists every retirement plan under it.
- `filer_size`: large = files Schedule H (generally 100+ participants; has providers and fees); small = 5500-SF or Schedule I.
- `include_ended` (boolean): Include plans that are terminated, merged into another plan, or stopped filing. Off by default.
- `limit` (integer): Results per page (1-50).
- `max_assets`: Maximum end-of-year net assets in dollars.
- `max_participants`: Maximum end-of-year total participants.
- `min_assets`: Minimum end-of-year net assets in dollars, latest plan year.
- `min_participants`: Minimum end-of-year total participants.
- `name`: Company or plan name, as you know it. Fuzzy: typos, missing suffixes (Inc, LLC), DBA names and former names all match, and the last word can be a prefix ("acm" for Acme). Results come best match firs…
- `offset` (integer): Results to skip (0-500).
- `plan_type`: Plan type: 401k, 403b, cash_balance, db_and_dc, defined_benefit, esop, ira_based, money_purchase, other_dc, profit_sharing, stock_bonus, target_benefit, type_not_coded, db, dc. `dc` = any defined con…
- `recordkeeper`: Recordkeeper, any brand old or new ("Empower", "Great-West", "Fidelity"). Matched to the firm's family, so Great-West and Prudential filings count as Empower. Only plans that filed a Schedule C can m…
- `state`: Two-letter state of the sponsor's address, e.g. TX.

### `get_plan` (~250 tokens)

Latest clean profile of one plan

The plan as of its latest filing: identity and status, plan type and features, assets and
participants, average balance and approximate return, recordkeeper, advisors and auditor, headline fees,
screening signals and data-quality flags.

When the latest year is a small-plan filing (no Schedule C), the recordkeeper shown is the last one seen
on an earlier Schedule C, labeled with its year and a lower confidence. `availability` says which years
\`get_plan_history` and `get_plan_fees` will return.

Price: $0.03 per call, paid in USDC on Base (mainnet) with x402 (MCP transport), or from card credits (an app signed in at /connect, or an 'Authorization: Bearer <key>' header). Without payment the tool returns the payment requirements. Errors and empty results aren't charged.

Same data as GET /plan of the Plan Data API.

Input parameters:

- `ein` (string, required): Sponsor EIN (9 digits, dashes allowed).
- `pn`: Plan number (1-999; 1 and 001 both work). Optional when the EIN sponsors only one retirement plan; otherwise the error lists the plans to choose from.

### `get_plan_history` (~209 tokens)

Every plan year of one plan: assets, participants, growth breakdown, providers, events

One entry per plan year, oldest first: the filing used, assets and participants, average balance,
approximate return, participant growth (flagged across the 2023 counting change), the growth breakdown
(contributions, investment return, distributions, expenses, transfers), plan-paid expenses and Schedule C
fees in bps, the year's recordkeeper / primary advisor / auditor, and the change events detected that
year.

Price: $0.25 per call, paid in USDC on Base (mainnet) with x402 (MCP transport), or from card credits (an app signed in at /connect, or an 'Authorization: Bearer <key>' header). Without payment the tool returns the payment requirements. Errors and empty results aren't charged.

Same data as GET /plan/history of the Plan Data API.

Input parameters:

- `ein` (string, required): Sponsor EIN (9 digits, dashes allowed).
- `pn`: Plan number (1-999). Optional when the EIN has one plan.

### `get_plan_fees` (~276 tokens)

Schedule C fee breakdown in dollars and bps, with completeness notes

For each large plan year: Schedule C pay by role (recordkeeping, advisory, participant advice, TPA,
investment management, trustee, other) in dollars and basis points of average net assets; every provider
on the Schedule C with names as filed, codes, direct and indirect pay; Schedule H line 2i expenses as a
second view; and a completeness rating with the reasons.

Small plans file no Schedule C: the response still succeeds, with `schedule_c_available: false` and the
plan-paid expenses that small plans do report. Years with no Schedule C return no breakdown and aren't
charged. Fees are floors: see `meta.coverage_notes`.

Price: $0.10 per call, paid in USDC on Base (mainnet) with x402 (MCP transport), or from card credits (an app signed in at /connect, or an 'Authorization: Bearer <key>' header). Without payment the tool returns the payment requirements. Errors and empty results aren't charged.

Same data as GET /fees of the Plan Data API.

Input parameters:

- `ein` (string, required): Sponsor EIN (9 digits, dashes allowed).
- `plan_year`: One plan year only. Default: every year.
- `pn`: Plan number (1-999). Optional when the EIN has one plan.

### `find_plan_changes` (~826 tokens)

Change events across plans: recordkeeper switches, new plans, mergers, terminations...

Change events detected by comparing each plan's consecutive filings, newest filing first. Each event
has before/after values, a confidence, the year compared against, a plain-English detail and the ACK ID
of the filing that shows it.

Providers are compared by family, so a rebrand (Great-West → Empower) isn't a change. A move caused by a
sale of the old recordkeeper's business (Securian → The Standard, Prudential → Empower; the list is at
\`get_coverage` `book_sales`) is a `recordkeeper_sold` event, not a `recordkeeper_change` switch: the sponsor
didn't choose it. Each event also has the plan's size around the event (`net_assets_at_event`), which
\`min_assets` and `sort=assets` use. The newest plan year is still being filed, so its counts grow month to
month.

Price: $0.25 per call, paid in USDC on Base (mainnet) with x402 (MCP transport), or from card credits (an app signed in at /connect, or an 'Authorization: Bearer <key>' header). Without payment the tool returns the payment requirements. Errors and empty results aren't charged.

Same data as GET /changes of the Plan Data API.

Input parameters:

- `ein`: Only this sponsor's plans (EIN, 9 digits, dashes allowed): what changed at one company.
- `event_type`: Event type(s); repeat the parameter or separate with commas. One of: recordkeeper_change, recordkeeper_sold, advisor_added, advisor_removed, advisor_changed, auditor_change, audit_opinion_change, lat…
- `filer_size`: large or small, in the event's plan year.
- `from_recordkeeper`: Only recordkeeper_change events (switches) away from this recordkeeper family (any brand name). Combine with `to_recordkeeper` for one move, e.g. Empower to Fidelity. Add event_type=recordkeeper_sold…
- `limit` (integer): Events per page (1-50). Each event is about 200 tokens of JSON, so the default 25 keeps an answer compact; narrow the filters rather than asking for more.
- `min_assets`: Minimum net assets around the event (`net_assets_at_event`: the larger of the event year's start and end).
- `min_confidence` (string): Lowest confidence to include: high = high only, medium = high and medium, low = all.
- `offset` (integer): Events to skip (0-500).
- `plan_type`: Plan type, as in `search_plans` (e.g. 401k, dc, db).
- `plan_year_from`: Earliest plan year of the event.
- `plan_year_to`: Latest plan year of the event.
- `pn`: With `ein`: only this plan number.
- `recordkeeper`: Only recordkeeper_change events (switches) to or from this recordkeeper family (any brand name works). Add event_type=recordkeeper_sold to see moves caused by a sale too.
- `since`: Only events whose filing DOL received on or after this date (YYYY-MM-DD): "what's new since I last checked". Excludes filings_stopped, which no filing reveals.
- `sort` (string): newest (the default: newest filing first) or assets (largest plan first, by `net_assets_at_event`).
- `state`: Two-letter state of the sponsor (latest filing).
- `to_recordkeeper`: Only recordkeeper_change events (switches) to this recordkeeper family (any brand name): plans it won. Moves caused by a sale aren't wins; add event_type=recordkeeper_sold to see them.

### `list_prospects` (~711 tokens)

Bulk list of plans by industry, place and size: address, industry, participants, assets, inception date, recordkeeper

A list of plans for prospecting or research, many per call: plan and sponsor name, mailing address,
EIN and plan number, industry, plan type, effective (inception) date, participants and net assets at the
end of the latest plan year, form type, recordkeeper and primary advisor last seen on Schedule C, and the
filing's ACK ID.

Filter by industry, place (state, city, ZIP), size, plan type, effective date or recordkeeper. Large
(long-form) filers only unless `filer_size` says otherwise. Use `search_plans` instead to find one company's
plan by name, and `get_plan` for everything about one plan. Paging stops at offset 500: narrow the
filters to see more.

Price: $0.25 per call, paid in USDC on Base (mainnet) with x402 (MCP transport), or from card credits (an app signed in at /connect, or an 'Authorization: Bearer <key>' header). Without payment the tool returns the payment requirements. Errors and empty results aren't charged.

Same data as GET /prospects of the Plan Data API.

Input parameters:

- `city`: Sponsor's city, as on the filing (case doesn't matter). Best with `state`.
- `effective_after`: Only plans whose effective (inception) date is on or after this date (YYYY-MM-DD).
- `effective_before`: Only plans whose effective (inception) date is on or before this date (YYYY-MM-DD).
- `filer_size` (string): large (the default) = long-form filers: Form 5500 with Schedule H, generally 100+ participants, with providers on Schedule C. small = 5500-SF or Schedule I. any = both.
- `include_ended` (boolean): Include plans that are terminated, merged into another plan, or stopped filing. Off by default.
- `industry`: The sponsor's industry: words ("restaurants", "car dealers", "law firms") or a NAICS business code or its start ("62" = health care, "5411" = legal services). Separate several with commas. `meta.quer…
- `limit` (integer): Plans per page (1-100). The price is per call, whatever the limit.
- `max_assets`: Maximum end-of-year net assets in dollars.
- `max_participants`: Maximum end-of-year participants.
- `min_assets`: Minimum end-of-year net assets in dollars, in the plan's latest plan year.
- `min_participants`: Minimum end-of-year participants, in the plan's latest plan year.
- `offset` (integer): Plans to skip (0-500).
- `plan_type`: Plan type, as in `search_plans` (e.g. 401k, dc, db).
- `recordkeeper`: Only plans whose latest Schedule C names this recordkeeper (any brand, matched to its family as in `search_plans`).
- `sort` (string): assets (largest first, the default), participants (most first), name (A-Z by sponsor) or newest_plan (latest effective date first).
- `state`: Two-letter state of the sponsor's address, e.g. OH.
- `zip`: Sponsor's ZIP code or its start (3-5 digits), e.g. 432 for the Columbus, OH area.

### `get_coverage` (~64 tokens)

Data coverage and limitations

What the data covers per plan year, every limitation, the coverage-note codes responses can carry,
the event types, the screening signals and the plan-type values. Free.

Also lists the prices and what isn't charged. Same data as GET /coverage of the Plan Data API.

### `get_account` (~113 tokens)

Your credit balance, and how to add more

How this connection pays, its credit balance in dollars, each tool's price, and a link where the person can add credit by card. Call it when the person asks what's left or how to pay, or to connect another device to the same balance. Free. It returns no plan data.

Input parameters:

- `new_device_code` (boolean): true = also make a one-time code (good for 15 minutes) that connects an app on another device to this same balance without paying again. Only when the person asks for it.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-form5500data-plan-data/api#diagnostics

## Score history

- 2026-11-21: 73
- 2026-11-20: 73
- 2026-11-19: 72
- 2026-11-18: 72
- 2026-11-17: 72
- 2026-11-16: 71
- 2026-11-15: 71
- 2026-11-14: 70
- 2026-11-13: 70
- 2026-11-12: 69
- 2026-11-11: 69
- 2026-11-10: 68
- 2026-11-09: 68

## Common questions

### What is the Plan Data API MCP server?

Plan Data API is an MCP server listed in the public MCP registry as com.form5500data/plan-data. Form 5500 data for prospecting and research: U.S. retirement plans, recordkeepers, fees, switches. This page covers its hosted endpoint (https://api.form5500data.com/mcp).

### Is the Plan Data API MCP server safe to use?

Plan Data API scores 73 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 Plan Data API MCP server expose?

Plan Data API exposes 8 tools: search_plans, get_plan, get_plan_history, get_plan_fees, find_plan_changes, and 3 more. Their descriptions and schemas cost roughly 3,036 tokens of context every time the server is loaded.

### Does the Plan Data API MCP server require authentication?

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

### Is the Plan Data API MCP server still maintained?

Plan Data API 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 Plan Data API MCP server?

VerifyMCP ran 13 checks on Plan Data API, 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://api.form5500data.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-form5500data-plan-data/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-form5500data-plan-data/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-form5500data-plan-data/api.json
- HTML version of this page: https://verifymcp.io/servers/com-form5500data-plan-data/api
