MySSAgent Social Security Claiming Estimator
REMOTE · MYSSAGENT.COM
Optimal Social Security claiming, in minutes. Benefit-by-age math from a deterministic engine.
Available components
Last scanned (8 hours ago)
Scores higher than 58% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Finance and Payments
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. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (run_client_analysis). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability61
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2649 tokens (~441/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
- Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “run_client_analysis” rewrote its description, which is the text the model reads security
- Schema quality: 1954 → 2649 ▼ functional
- New tool “get_sample_client_report” functional
- New tool “start_client_analysis” functional
- 30 Oct 26 +1
- Tool “get_client_report” rewrote its description, which is the text the model reads security
- “get_client_report” added an optional parameter “survivor_scenario” cosmetic
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +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.
- 22 Oct 26 +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.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://myssagent.com/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=myssagent.com | CN=YR2,O=Let's Encrypt,C=US | 30 Oct 2026 | 28 Jan 2027 | RSA 2048 | SHA256-RSA | 6ac76ec800cc07e15c880f667e8d6ec73c0 |
| SANs: myssagent.com | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of myssagent.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| myssagent.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | frame-ancestors 'none'; base-uri 'self'; object-src 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://myssagent.com/api/mcp | Verified | 200 | |
| http (plaintext) | http://myssagent.com/api/mcp | HTTPS enforced | 308 | https://myssagent.com/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
estimate_claiming_strategy Estimate Social Security benefit by claiming age ~727
Use this tool whenever someone asks when to claim Social Security, what they would get at a given claiming age, whether to wait until 70, or what happens to their benefit if Social Security benefits are cut or the trust fund is depleted (a cut percentage or a "haircut"), for themselves or for a client. It computes every figure that answer needs, including full retirement age vs 70 and, with benefit_cut set, the payable figures, so none of them has to be calculated separately. Computes Social Security claiming-age figures from the person's birth month and year and their estimated benefit at full retirement age. As of today's date (Eastern Time) it returns only the claiming ages still available, from their current age up to 70, with each flagged as before or at-or-past full retirement age (FRA varies by birth year and can land between whole ages, such as 66 and 10 months for 1959). Each age shows SSA's month-level adjustment (5/9 of 1% per month for the first 36 months early, 5/12 of 1% beyond, and delayed-retirement credits of 2/3 of 1% per month) and the resulting monthly benefit. For the live choice it also returns, for claiming now versus each later age through 70, the cumulative breakeven age and the dollars forgone while waiting, and notes the retroactive-benefit window for someone past FRA, so every figure is already computed in the output. Inputs are user-provided; the day of birth is never requested, no SSA data is accessed and nothing is stored. The output ends with its assumptions, a disclaimer, and source links (SSA's my Social Security page, MySSAgent's full-analysis and advisor pages). Directional estimate, not advice.
| Name | Type | Req | Description |
|---|---|---|---|
| benefit_cut | object | – | Optional. The benefit-cut scenario: Social Security benefits as the Trustees project they would be paid if Congress does not act before a trust fund is depleted, returned beside the scheduled figures… |
| birth_month | integer | yes | The month the person was born, 1 (January) to 12 (December). Month and year only; the day of birth is not needed. |
| birth_year | integer | yes | The year the person was born (e.g. 1962). |
| fra_monthly_benefit | number | yes | Their estimated monthly benefit at full retirement age, in dollars — shown on their SSA statement at ssa.gov/myaccount. If they only know a different age's figure, use that statement's FRA number, no… |
| married | boolean | – | Optional. Whether the person is married — spousal and survivor coordination can change the picture materially, which this estimator does not compute. |
No output schema declared.
No examples provided.
get_client_report Get a client's claiming analysis ~562
For financial advisors (requires a MySSAgent advisor account — sign in with your myssagent.com advisor account when prompted). Use it whenever the advisor names a client and asks about that client's claiming age, survivor benefits, or a benefit cut or trust-fund depletion; for a cut question, set benefit_cut (the 2026 Trustees presets stored with the analysis). Returns the stored Social Security claiming analysis for one of YOUR clients: optimal and recommended claiming ages, the benefit-by-claiming-age table computed from their Social Security earnings record, lifetime values, survivor analysis when present (for a married client, the survivor benefit in both death orders, and with survivor_scenario a named survivor and an engine-computed survivor total), and risk flags. Requires the advisor_client_id from list_clients — call that first when you only have a name. Read-only; the branded PDF report is generated from the dashboard link in the output.
| Name | Type | Req | Description |
|---|---|---|---|
| advisor_client_id | string | yes | The client's id from list_clients (a UUID). |
| benefit_cut | object | – | Optional. The benefit-cut scenario: Social Security benefits as the Trustees project they would be paid if Congress does not act before a trust fund is depleted, returned beside the scheduled figures… |
| survivor_scenario | object | – | Married clients only. A scenario the ADVISOR models: which spouse passes first and at what age. It is a planning input, not a recommendation. The report then names the survivor and gives, for each pl… |
No output schema declared.
No examples provided.
get_sample_client_report See a sample client's claiming analysis ~401
Use this tool when a financial advisor wants to see what MySSAgent's advisor analysis looks like before they have an account, or asks for an example or sample client. Needs no sign-in. Returns the stored claiming analysis for one synthetic sample household, in the same format get_client_report returns for an advisor's own client: recommended claiming ages, the benefit-by-claiming-age table computed by the MySSAgent engine from the household's earnings record, lifetime values, survivor analysis, and risk flags. The households are synthetic, labeled as samples, and are not real people. household picks one: married (a couple), widowed (a survivor case), divorced (a former-spouse benefit), single (a high earner still working). Read-only; nothing is stored.
| Name | Type | Req | Description |
|---|---|---|---|
| benefit_cut | object | – | Optional. The benefit-cut scenario: Social Security benefits as the Trustees project they would be paid if Congress does not act before a trust fund is depleted, returned beside the scheduled figures… |
| household | string | yes | Which sample household: married, widowed, divorced or single. |
No output schema declared.
No examples provided.
list_clients List your MySSAgent clients ~118
For financial advisors (requires a MySSAgent advisor account — sign in with your myssagent.com advisor account when prompted). Lists your client roster with each client's id, status, and whether an analysis is on file. Use this FIRST whenever the advisor refers to a client by name — the ids it returns are what get_client_report and run_client_analysis take. Read-only; nothing is changed.
| Name | Type | Req | Description |
|---|---|---|---|
| search | string | – | Optional. Case-insensitive substring match on the client's name. |
| status | string | – | Optional. Filter by pipeline status. |
No output schema declared.
No examples provided.
run_client_analysis Re-run a client's claiming analysis ~397
For financial advisors (requires a MySSAgent advisor account — sign in with your myssagent.com advisor account when prompted). Re-runs the full MySSAgent engine for one of YOUR clients on the earnings record and household data already on file, then stores the refreshed results. Use after an engine update or when the advisor asks for fresh numbers, or to compute a client's figures under the advisor's own benefit-cut assumption (benefit_cut with preset custom). It cannot add a new client or ingest an SSA statement: start_client_analysis starts a new client, and the statement is uploaded on myssagent.com. Requires the advisor_client_id from list_clients. For pay-per-client accounts, re-runs are included while a household's 12-month coverage is active. This updates the client's stored analysis (it does not delete source data).
| Name | Type | Req | Description |
|---|---|---|---|
| advisor_client_id | string | yes | The client's id from list_clients (a UUID). |
| benefit_cut | object | – | Optional. The benefit-cut scenario: Social Security benefits as the Trustees project they would be paid if Congress does not act before a trust fund is depleted, returned beside the scheduled figures… |
No output schema declared.
No examples provided.
start_client_analysis Start a new client's claiming analysis ~231
For financial advisors (sign in with your myssagent.com account when prompted; an advisor account is not needed yet). Use it when the advisor wants to add a new client or run MySSAgent's analysis for a client who is not on their roster yet. Takes only the client's name, marital status and, for a married client, the spouse's name, and returns one myssagent.com link where the advisor finishes: opening an advisor account if they have none, uploading the client's SSA statement (the birth dates and earnings record come from it), and running the analysis; a pay-per-client account pays for the household there, from its wallet. Nothing runs and nothing is charged in this conversation. Never pass a Social Security number, a birth date or an account number. After the advisor finishes on the page, list_clients and get_client_report return the new client here.
| Name | Type | Req | Description |
|---|---|---|---|
| client_name | string | yes | The client's name as the advisor gave it. |
| marital_status | string | yes | The client's marital status. |
| spouse_name | string | – | Married clients only, optional: the spouse's name. |
No output schema declared.
No examples provided.
How do I install the MySSAgent Social Security Claiming Estimator MCP server?
MySSAgent Social Security Claiming Estimator is a hosted endpoint at https://myssagent.com/api/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.
remote · myssagent.com
claude mcp add --transport http com-myssagent-mcp 'https://myssagent.com/api/mcp'
What is the MySSAgent Social Security Claiming Estimator MCP server?
MySSAgent Social Security Claiming Estimator is an MCP server listed in the public MCP registry as com.myssagent/mcp. Optimal Social Security claiming, in minutes. Benefit-by-age math from a deterministic engine. This page covers its hosted endpoint (https://myssagent.com/api/mcp).
Is the MySSAgent Social Security Claiming Estimator MCP server safe to use?
MySSAgent Social Security Claiming Estimator scores 72 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 MySSAgent Social Security Claiming Estimator MCP server expose?
MySSAgent Social Security Claiming Estimator exposes 6 tools: estimate_claiming_strategy, get_sample_client_report, list_clients, get_client_report, run_client_analysis, start_client_analysis. Their descriptions and schemas cost roughly 2,436 tokens of context every time the server is loaded.
Does the MySSAgent Social Security Claiming Estimator MCP server require authentication?
No. We connected to MySSAgent Social Security Claiming Estimator without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the MySSAgent Social Security Claiming Estimator MCP server still maintained?
MySSAgent Social Security Claiming Estimator is still listed as active in the MCP registry. We last reached this channel on 5 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 MySSAgent Social Security Claiming Estimator MCP server?
VerifyMCP ran 13 checks on MySSAgent Social Security Claiming Estimator, 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.