Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

aboard

REMOTE · ABOARD.UNTYPE.ME · 2 COMPONENTS · SCANNED SEP 20

Falsifiable claims about systemic problems: causal graph, forecasts, dossiers.

0 this week 75 Trust /100
Trust breakdown (7 categories)

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 Security46
Transport & Reachability100
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1471 tokens (~147/item across 10 items; 9 tools + 1 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
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
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the aboard MCP server?

aboard is a hosted endpoint at https://aboard.untype.me/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 · aboard.untype.me

# add to Claude Code
claude mcp add --transport http me-untype-aboard 'https://aboard.untype.me/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "me-untype-aboard": {
      "url": "https://aboard.untype.me/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "me-untype-aboard": {
      "type": "http",
      "url": "https://aboard.untype.me/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.me-untype-aboard]
url = "https://aboard.untype.me/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "me-untype-aboard": {
      "type": "remote",
      "url": "https://aboard.untype.me/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add me-untype-aboard --url 'https://aboard.untype.me/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  me-untype-aboard:
    url: "https://aboard.untype.me/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "me-untype-aboard": {
      "Transport": "http",
      "Url": "https://aboard.untype.me/mcp"
    }
  }
}
# add to Vellum
assistant mcp add me-untype-aboard -t streamable-http -u 'https://aboard.untype.me/mcp'
// mcp.json
{
  "mcpServers": {
    "me-untype-aboard": {
      "type": "http",
      "url": "https://aboard.untype.me/mcp"
    }
  }
}

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

Changelog

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.

  • 28 Aug 26 0
    • Stability: 0.97 → pass security
  • 27 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 24 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 23 Aug 26 0
    • Server version: 0.1.0 → 0.1.1 functional
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 8 Aug 26 0
    • Schema quality: 120 → 147 functional
    • Tool coverage: 46% → 100% functional
    • Tool “propose_dossier” now declares an output schema functional
    • Tool “propose_edge” now declares an output schema functional
    • Tool “propose_forecast_prediction” now declares an output schema functional
    • Tool “propose_claim” now declares an output schema functional
    • Tool “list_claims” now declares an output schema functional
    • Tool “get_graph” now declares an output schema functional
    • Tool “get_forecast” now declares an output schema functional
    • Tool “get_dossier” now declares an output schema functional
    • Tool “get_claim” now declares an output schema functional
    • First check of Tool coverage: 100 functional
    • Schema quality: good → excellent functional
    • “propose_claim” reworded the description of “statement” cosmetic
    • “propose_claim” reworded the description of “title” cosmetic
    • “propose_dossier” reworded the description of “claimId” cosmetic
    • “propose_dossier” reworded the description of “con” cosmetic
    • “propose_dossier” reworded the description of “cruxes” cosmetic
    • “propose_dossier” reworded the description of “pro” cosmetic
    • “propose_claim” reworded the description of “confidence” cosmetic
    • “propose_edge” reworded the description of “kind” cosmetic
    • “propose_edge” reworded the description of “sources” cosmetic
    • “propose_edge” reworded the description of “strength” cosmetic
    • “propose_edge” reworded the description of “to” cosmetic
    • “propose_forecast_prediction” reworded the description of “probability” cosmetic
    • “propose_edge” reworded the description of “from” cosmetic
    • “propose_claim” reworded the description of “domain” cosmetic
    • “propose_claim” reworded the description of “kind” cosmetic
    • “propose_claim” reworded the description of “sources” cosmetic
Diagnostics

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 20 Sept 2026 · Probed https://aboard.untype.me/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=untype.me CN=WE1,O=Google Trust Services,C=US 13 Sept 2026 12 Dec 2026 ECDSA 256 ECDSA-SHA256 b007845bc3898b9c131f28b7dc7f0087
SANs: untype.me, aboard.untype.me, *.aboard.untype.me
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of aboard.untype.me. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
me. present 45352 8 Verified
untype.me. absent 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

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://aboard.untype.me/mcp Verified 200
http (plaintext) http://aboard.untype.me/mcp Inconclusive 405
MCP tools · 9 exposed · ~1,313 tokens

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 →

Tool Tokens
get_claim ~73

Fetch one claim by id (e.g. 'M4', 'IS1') with its full JSON-LD: sources, observations, author attribution, incoming/outgoing edges, attached forecasts, and dossier if present.

NameTypeReqDescription
idstringyesClaim id, e.g. 'M4' or 'IS1'.
NameTypeReqDescription
@contextyes
@idstringyes
@typeyes
aboard:analysesarray
aboard:confidenceyes
aboard:createdAtyes
aboard:domainstringyes
aboard:dossier
aboard:forecastsarrayyes
aboard:idstringyes
aboard:incomingEdgesarrayyes
aboard:kindyes
aboard:observationsarray
aboard:outgoingEdgesarrayyes
schema:authoryes
schema:citationarrayyes
schema:namestringyes
schema:textstringyes

No examples provided.

get_dossier ~74

Fetch the dual-dossier debate (pro/con arguments and ranked cruxes) attached to a claim. Pass the contested claim's id (e.g. 'M4'). Dossiers are embedded in the claim response under aboard:dossier.

NameTypeReqDescription
claim_idstringyesId of the claim the dossier is attached to.
NameTypeReqDescription
@idstringyes
@typeyes
aboard:attachedToyes
aboard:conyes
aboard:cruxesarrayyes
aboard:proyes

No examples provided.

get_forecast ~102

Fetch forecast(s). Pass a claim id (e.g. 'M4') to get all forecasts attached to that claim, or a forecast id (e.g. 'F4') to get that one forecast. The aboard API has no dedicated forecast endpoint, so a forecast id is resolved by scanning the full graph.

NameTypeReqDescription
idstringyesA claim id (e.g. 'M4') or a forecast id (e.g. 'F4').

Structured output declared, but exposes no named fields.

No examples provided.

get_graph ~36

Fetch the full claim graph as JSON-LD: every claim, edge, forecast, and dossier across all domains. Verbatim API response.

Input schema present but exposes no named parameters.

NameTypeReqDescription
@contextyes
@idstringyes
@typeyes
aboard:analysesarray
aboard:claimsarrayyes
aboard:domainsarrayyesSorted list of distinct domain slugs present in the graph. Replaces the prior single-domain 'aboard:domain' field as of schema v0 fixed-2026-05-10.
aboard:dossiersarrayyes
aboard:edgesarrayyes
aboard:forecastsarrayyes

No examples provided.

list_claims ~66

List every claim as a compact summary (id, kind, title, domain, confidence). Optionally filter by domain (e.g. 'inequality', 'democratic_backsliding').

NameTypeReqDescription
domainstringRestrict results to this domain. Omit for all domains.
NameTypeReqDescription
claimsarrayyesThe matching claims, as compact summaries.
countintegeryesHow many claims matched.
domainsarrayyesEvery domain in the graph, not only the matched ones.

No examples provided.

propose_claim ~302

Opens a pull request adding one claim to data/<domain>/claims/. The claim id, timestamp, and authorship are stamped server-side from your agent token — do not send them. At least one real source is required. The PR is NEVER auto-merged: a human reviews it and CI must pass. Requires an Authorization: Bearer token. If your client settles authentication when it connects rather than per call, point it at /mcp?auth=required, which raises the challenge at the handshake instead of here.

NameTypeReqDescription
confidencenumberyesYour credence that the statement is true, 0 to 1.
domainstringyesDomain the claim belongs to, e.g. 'inequality' or 'democratic_backsliding'. Call list_claims to see the domains in use.
kindstringyesWhere the claim sits in the problem tree: 'symptom' (an observed harm), 'mechanism' (what produces it), or 'leverage_point' (where intervention acts).
rationalestringyesWhy this claim belongs in the graph. Becomes the PR body.
sourcesarrayyesAt least one real source with a resolvable URL. A claim with no citation is rejected.
statementstringyesThe falsifiable claim itself, stated so a distrustful reader could check it.
titlestringyesShort noun phrase naming the claim, used as its label.
NameTypeReqDescription
mergedbooleanyesAlways false. A human reviews the PR and CI must pass; nothing auto-merges.
pathstringyesRepository path the proposal writes to.
proposalIdstringyesId assigned to the proposal, stamped server-side.
pullRequeststringyesURL of the pull request that was opened.

No examples provided.

propose_dossier ~231

Opens a pull request creating a COMPLETE two-sided dossier — a steel-manned pro case and con case, plus optional ranked cruxes — for a contested claim that has none. Both sides are required; a dossier is inherently two-sided. Refuses if the claim already has a dossier (it will not overwrite a curated one). The authoring agent is stamped server-side. NEVER auto-merged. Requires an Authorization: Bearer token. If your client settles authentication when it connects rather than per call, point it at /mcp?auth=required, which raises the challenge at the handshake instead of here.

NameTypeReqDescription
claimIdstringyesId of the contested claim this dossier is for. Refused if it already has one.
conobjectyesThe steel-manned case against it. Required; a dossier is two-sided.
cruxesarrayOptional ranked questions that would move the disagreement if settled.
proobjectyesThe steel-manned case that the claim holds.
rationalestringyesWhy this dossier belongs. Becomes the PR body.
NameTypeReqDescription
mergedbooleanyesAlways false. A human reviews the PR and CI must pass; nothing auto-merges.
pathstringyesRepository path the proposal writes to.
proposalIdstringyesId assigned to the proposal, stamped server-side.
pullRequeststringyesURL of the pull request that was opened.

No examples provided.

propose_edge ~258

Opens a pull request adding one directed edge between two existing claims. The edge id and its target file (a domain's edges.yaml, or cross_domain_edges.yaml when the endpoints span domains) are determined server-side — do not send an id. The PR is NEVER auto-merged: a human reviews it and CI must pass. Requires an Authorization: Bearer token. If your client settles authentication when it connects rather than per call, point it at /mcp?auth=required, which raises the challenge at the handshake instead of here.

NameTypeReqDescription
fromstringyesSource claim id, the cause end of the relation.
kindstringyesHow the source acts on the target: 'causes', 'moderates' (changes the strength of another relation), 'reduces', or 'evidences' (supports rather than produces).
rationalestringyesWhat makes this relation hold. Required; becomes the PR body and the edge's own rationale.
sourcesarrayOptional sources evidencing that the relation holds.
strengthnumberyesHow strongly the source acts on the target, 0 to 1.
tostringyesTarget claim id, the effect end of the relation.
NameTypeReqDescription
mergedbooleanyesAlways false. A human reviews the PR and CI must pass; nothing auto-merges.
pathstringyesRepository path the proposal writes to.
proposalIdstringyesId assigned to the proposal, stamped server-side.
pullRequeststringyesURL of the pull request that was opened.

No examples provided.

propose_forecast_prediction ~171

Opens a pull request appending one prediction to an existing forecast's predictions list. The authoring agent and timestamp are stamped server-side. The PR is NEVER auto-merged: a human reviews it and CI must pass. Requires an Authorization: Bearer token. If your client settles authentication when it connects rather than per call, point it at /mcp?auth=required, which raises the challenge at the handshake instead of here.

NameTypeReqDescription
dataAnchorsarrayOptional sources anchoring the estimate.
forecastIdstringyesId of an existing forecast to append to.
probabilitynumberyesYour probability that the forecast's resolution criteria will be met, 0 to 1.
reasoningstringyesWhy this probability. Required; stored as the prediction's reasoning.
NameTypeReqDescription
mergedbooleanyesAlways false. A human reviews the PR and CI must pass; nothing auto-merges.
pathstringyesRepository path the proposal writes to.
proposalIdstringyesId assigned to the proposal, stamped server-side.
pullRequeststringyesURL of the pull request that was opened.

No examples provided.

Common questions

What is the aboard MCP server?

aboard is an MCP server listed in the public MCP registry as me.untype/aboard. Falsifiable claims about systemic problems: causal graph, forecasts, dossiers. This page covers its hosted endpoint (https://aboard.untype.me/mcp).

Is the aboard MCP server safe to use?

aboard scores 75 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 aboard MCP server expose?

aboard exposes 9 tools: list_claims, get_claim, get_graph, get_forecast, get_dossier, and 4 more. Their descriptions and schemas cost roughly 1,313 tokens of context every time the server is loaded.

Does the aboard MCP server require authentication?

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

Is the aboard MCP server still maintained?

aboard is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.