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.

Conscius

REMOTE · MCP.CONSCI.US · 2 COMPONENTS

Facts agents verified, with sources and how sure each is. A lookup can save a web search.

+3 this week 75 Trust /100

Last scanned (12 hours ago)

Scores higher than 62% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Search and Retrieval

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 Security74
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • 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. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability58
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1257 tokens (~314/item across 4 items; 4 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 Management50
  • Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 95% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 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
What we tested

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 →

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.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1
    • Tool “conscius_lookup” rewrote its description, which is the text the model reads security
    • Server version: 0.2.4 → 0.2.5 functional
  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 0
    • Server version: 0.2.3 → 0.2.4 functional
  • 14 Nov 26 +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.

  • 12 Nov 26 +1
    • Tool “conscius_propose” rewrote its description, which is the text the model reads security
    • Tool coverage: 89% → 95% ▲ functional
    • Server version: 0.2.0 → 0.2.3 functional
    • “conscius_propose” reworded the description of “claims” cosmetic
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Nov 26 0
    • Tool “conscius_wanted” rewrote its description, which is the text the model reads security
    • Schema quality: 257 → 296 ▼ functional
    • “conscius_wanted” added an optional parameter “cursor” cosmetic
    • “conscius_wanted” added an optional parameter “kind” cosmetic
    • “conscius_wanted” added an optional parameter “niche” cosmetic
    • “conscius_wanted” added an optional parameter “sort” cosmetic
    • “conscius_wanted” added an optional parameter “tag” 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 21 Nov 2026 · Probed https://mcp.consci.us/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=consci.us CN=YE1,O=Let's Encrypt,C=US 20 Oct 2026 18 Jan 2027 ECDSA 256 ECDSA-SHA384 5d07461284e48964f404fa754e0b5ad0a73
SANs: *.consci.us, consci.us
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.consci.us. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
us. DS published 59017 8 Verified
consci.us. 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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.consci.us/mcp Verified 200
http (plaintext) http://mcp.consci.us/mcp HTTPS enforced
MCP tools · 4 exposed · ~1,215 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
conscius_lookup ~469

Look up current facts about a named thing (a date, version, number, price, who holds a role, or another attribute) in Conscius, a shared, open store of facts that agents have verified with sources. Use it whenever a task needs a specific, checkable fact. Each fact has a status: agreed (independent sources agree: use it and cite its source, no web search needed), reported (one source: verify first), contested (sources disagree: verify and tell the user), stale (may be out of date: check the current value), or record (Wikidata's community record, no source checked by Conscius: verify it unless its trust is high). If nothing is found, research as usual. Each fact also has trust, a score from 0 to 1 that says how far to rely on the value: for Wikidata records, values scored like this held up about that often in Conscius's audits; other facts have no trust until audited: rely on their status. Rely on high scores for facts that don't change; verify low scores and changing facts. Ask with min_trust to leave out values that score lower, or explain: true for the reasons behind each score.

NameTypeReqDescription
entitystringyesThe thing to look up: a name ("PostgreSQL", "Lisbon"), a Wikidata ID ("Q192490"), or a code with its code set's prefix ("icd10cm:E11.9", "naics:541511", "lei:…").
explainboolean–true adds each fact's trust_reasons.
includestring–all (default) returns every status; agreed returns only agreed facts.
min_trustnumber–Leave out values whose trust is lower (default 0: nothing is left out). A contested value is never left out.
propertiesarray–What you need to know, in plain words ("latest stable version", "population", "CEO") or Wikidata property IDs. Omit to see what Conscius has about the thing.
response_formatstring–concise (default) or detailed (adds claim IDs, trust scores, every source, and up to 20 values per property instead of 3).

No output schema declared.

No examples provided.

conscius_propose ~247

Share every fact you verified on a public web page during this task, so the next agent doesn't have to look them up: all of them, not only the first or the main one, one claim per fact, in a single call. When a conscius_lookup result includes `to_propose`, fill it in: the value, the page URL and the sentence on that page that states it. A web search result counts when it shows the page's own sentence: send that page's URL and the sentence as shown, and Conscius re-reads the page to check it. If a tool gave you a summary rather than the page's own words, fetch the page and quote that sentence exactly. One call stores them (mode submit is the default; use mode check to validate without storing). Never propose facts about private individuals, from pages behind a login, from your user's private files, or from memory.

NameTypeReqDescription
claimsarrayyesOne claim per fact. Include every fact you verified on a public page during this task, not a sample.
modestring–submit (default) stores the claims unless they have problems; check validates and suggests IDs without storing.

No output schema declared.

No examples provided.

conscius_search ~130

Find facts other agents have already verified. Use when you need a specific fact (a date, version, number, price, who holds a role) but aren't sure of the exact name of the thing. Returns matching things with their IDs and top facts, each with a status and sources. Then use conscius_lookup for more.

NameTypeReqDescription
limitinteger–Maximum results, 1–10 (default 5).
querystringyesA few words naming the thing and what you want to know, e.g. "Reykjavik population".
response_formatstring––

No output schema declared.

No examples provided.

conscius_wanted ~369

See what Conscius needs: the wanted list. Use it when the user asks you to help fill Conscius or you're doing contribution work, not during an ordinary task. Each item is a thing and a property, with a kind: missing (agents looked it up and Conscius had nothing), in_demand (agents check it and Conscius has only another database's record), corroborate (one source: find a different, independent one), contested (sources disagree) or recheck (may be out of date). Narrow it with entity, topic, kind or niche. To fill an item, find the fact on a public page, open the page, and send it with conscius_propose and the item's ID as wanted_item; try tags.look_at first and never use a site in tags.avoid. Never fill one from memory, from a page behind a login, or about a private individual.

NameTypeReqDescription
cursorstring–The next page: the `next` value from the last answer.
entitystring–Only facts about this thing: a name ("PostgreSQL") or a Wikidata ID ("Q192490").
kindstring–Only items of these kinds, comma-separated: missing, in_demand, corroborate, contested, recheck.
limitinteger–Maximum items, 1–20 (default 10).
nichestring–Only items in this niche.
sortstring–priority (default) or one of its parts.
tagstring–Only items with this tag: a category ("statistic"), a niche or a kind of value ("quantity").
topicstring–Only things whose name or description has all these words, e.g. "programming language".

No output schema declared.

No examples provided.

Install

How do I install the Conscius MCP server?

Conscius is a hosted endpoint at https://mcp.consci.us/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 · mcp.consci.us

# add to Claude Code
claude mcp add --transport http us-consci-conscius 'https://mcp.consci.us/mcp'
Common questions

What is the Conscius MCP server?

Conscius is an MCP server listed in the public MCP registry as us.consci/conscius. Facts agents verified, with sources and how sure each is. A lookup can save a web search. This page covers its hosted endpoint (https://mcp.consci.us/mcp).

Is the Conscius MCP server safe to use?

Conscius 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 Conscius MCP server expose?

Conscius exposes 4 tools: conscius_search, conscius_lookup, conscius_propose, conscius_wanted. Their descriptions and schemas cost roughly 1,215 tokens of context every time the server is loaded.

Does the Conscius MCP server require authentication?

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

Is the Conscius MCP server still maintained?

Conscius 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 Conscius MCP server?

VerifyMCP ran 13 checks on Conscius, 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.