Plan Data API MCP server
com.form5500data/plan-dataform5500data.comstreamable-httpv0.1.0Scanned
Form 5500 data for prospecting and research: U.S. retirement plans, recordkeepers, fees, switches.
7 tools: 7 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Plan Data API MCP server can do
The Plan Data API MCP server is published by form5500data.com, a domain the MCP Registry verified. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (get_coverage).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 9, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Only reads 7Show 7 read-only tools
find_plan_changesChange events detected by comparing each plan's consecutive filings, newest filing first.No findings
Why it is in this group
- The name "find_plan_changes" says "find": a word for reading.
Description, as the server wrote it 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. 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). 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.
Annotations the server declares
- title: Change events across plans: recordkeeper switches, new plans, mergers, terminations...
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_coverageWhat 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.Reads private dataNo findings
Why it is in this group
- The name "get_coverage" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "note": it reads notes.
Description, as the server wrote it 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.
Annotations the server declares
- title: Data coverage and limitations
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_planThe 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, …No findings
Why it is in this group
- The name "get_plan" says "get": a word for reading.
Description, as the server wrote it 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). 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.
Annotations the server declares
- title: Latest clean profile of one plan
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_plan_feesFor 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 ne…No findings
Why it is in this group
- The name "get_plan_fees" says "get": a word for reading.
Description, as the server wrote it 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. Check `get_plan` `availability.fee_years` first to see which years have a breakdown. Fees are floors: see `meta.coverage_notes`. Price: $0.10 per call, paid in USDC on Base (mainnet) with x402 (MCP transport). 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.
Annotations the server declares
- title: Schedule C fee breakdown in dollars and bps, with completeness notes
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_plan_historyOne entry per plan year, oldest first: the filing used, assets and participants, average balance, approximate return, participant growth (flagged across the 2023 counting change), …No findings
Why it is in this group
- The name "get_plan_history" says "get": a word for reading.
Description, as the server wrote it 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). 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.
Annotations the server declares
- title: Every plan year of one plan: assets, participants, growth breakdown, providers, events
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_prospectsA 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, participan…No findings
Why it is in this group
- The name "list_prospects" says "list": a word for reading.
Description, as the server wrote it 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). 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.
Annotations the server declares
- title: Bulk list of plans by industry, place and size: address, industry, participants, assets, inception date, recordkeeper
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_plansFind plans.No findings
Why it is in this group
- The name "search_plans" says "search": a word for reading.
Description, as the server wrote it 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). 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.
Annotations the server declares
- title: Find plans by company name, EIN, state, size, recordkeeper or plan type
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 16, 2026, 14:20 UTC, unchanged since Nov 16, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.form5500data.com/.well-known/oauth-protected-resource
- Authorization servers
- https://api.form5500data.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.form5500data.com/mcp: tools/list returned 8 tools to an anonymous client, including get_account (write)
Posture changes
- Nov 16, 2026
- Tools that change things, listed without credentials: 0 to 1
- RFC 9728 protected resource metadata: none to https://api.form5500data.com/.well-known/oauth-protected-resource
- Authorization servers: none to https://api.form5500data.com
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to no
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 0 -> 1; RFC 9728 protected resource metadata: none -> https://api.form5500data.com/.well-known/oauth-protected-resource; Authorization servers: none -> https://ap…View diff
- Tools that change things, listed without credentials: 0 to 1
- RFC 9728 protected resource metadata: none to https://api.form5500data.com/.well-known/oauth-protected-resource
- Authorization servers: none to https://api.form5500data.com
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to no
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http plan-data https://api.form5500data.com/mcpclaude mcp add --transport http plan-data https://api.form5500data.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__plan-data__search_plans",
"mcp__plan-data__get_plan",
"mcp__plan-data__get_plan_history",
"mcp__plan-data__get_plan_fees",
"mcp__plan-data__find_plan_changes",
"mcp__plan-data__list_prospects",
"mcp__plan-data__get_coverage"
],
"ask": [],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as plan-data. Review it before you use it.
Capability tags behind 1 rule
- mcp__plan-data__get_coverage private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.form5500data/plan-data/verify?hash=6d2972bdb4b37c46be82056e5acc5ea1dfdd51f8e9133cca25ac1daf90384612" | jq -e '.changed == false'Pinned hash 6d2972bdb4b3, from Nov 9, 2026, 00:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.form5500data/plan-data/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.form5500data/plan-data)Source: MCP Registry. Synced Nov 9, 2026, 00:17 UTC.
Plan Data API MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Plan Data API MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Plan Data API MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Plan Data API MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Plan Data API MCP server have?
- 7 tools: 7 read. search_plans, get_plan, get_plan_history, get_plan_fees, find_plan_changes, list_prospects and get_coverage.
Does the Plan Data API MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Plan Data API MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Plan Data API MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.