humanMCP — kapoost
REMOTE · KAPOOST.HUMANMCP.NET · SCANNED SEP 20
Personal MCP server for humans who create. Proof of authorship, license control.
Available components
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 Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 42 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- 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
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 5382 tokens (~128/item across 42 items; 42 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage70
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 11% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_skill" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 43 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
How do I install the humanMCP — kapoost MCP server?
humanMCP — kapoost is a hosted endpoint at https://kapoost.humanmcp.net/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 · kapoost.humanmcp.net
claude mcp add --transport http kapoost-humanmcp 'https://kapoost.humanmcp.net/mcp'
{
"mcpServers": {
"kapoost-humanmcp": {
"url": "https://kapoost.humanmcp.net/mcp"
}
}
} {
"servers": {
"kapoost-humanmcp": {
"type": "http",
"url": "https://kapoost.humanmcp.net/mcp"
}
}
} [mcp_servers.kapoost-humanmcp] url = "https://kapoost.humanmcp.net/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"kapoost-humanmcp": {
"type": "remote",
"url": "https://kapoost.humanmcp.net/mcp",
"enabled": true
}
}
} openclaw mcp add kapoost-humanmcp --url 'https://kapoost.humanmcp.net/mcp' --transport streamable-http
mcp_servers:
kapoost-humanmcp:
url: "https://kapoost.humanmcp.net/mcp" {
"McpServers": {
"kapoost-humanmcp": {
"Transport": "http",
"Url": "https://kapoost.humanmcp.net/mcp"
}
}
} assistant mcp add kapoost-humanmcp -t streamable-http -u 'https://kapoost.humanmcp.net/mcp'
{
"mcpServers": {
"kapoost-humanmcp": {
"type": "http",
"url": "https://kapoost.humanmcp.net/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 5 Sept 26 +9
- Judged manipulation: unverified → pass ▲ security
- Schema quality: unverified → good ▲ functional
- 4 Sept 26 −9
- Judged manipulation: pass → unverified ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: good → unverified ▼ functional
- 27 Aug 26 −1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “get_persona” rewrote its description, which is the text the model reads security
- Tool “get_skill” rewrote its description, which is the text the model reads security
- Tool “run_narada” rewrote its description, which is the text the model reads security
- Schema quality: 106 → 128 ▼ functional
- Tool coverage: 0% → 11% ▲ functional
- New tool “prepare_narada” functional
- “get_persona” added an optional parameter “session_token” cosmetic
- “get_skill” added an optional parameter “session_token” cosmetic
- “list_collection” added an optional parameter “session_token” cosmetic
- “load_skill_group” added an optional parameter “session_token” cosmetic
- “read_collection_item” added an optional parameter “session_token” cosmetic
- “recall” added an optional parameter “session_token” cosmetic
- “remember” added an optional parameter “session_token” cosmetic
- “run_narada” added an optional parameter “personas” cosmetic
- 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 0
- Stability: 0.97 → pass security
- 24 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.
- 21 Aug 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “suggest_skills” rewrote its description, which is the text the model reads security
- 14 Aug 26 0
- Tool “about_humanmcp” rewrote its description, which is the text the model reads security
- Tool “ask_human” rewrote its description, which is the text the model reads security
- Tool “bootstrap_session” rewrote its description, which is the text the model reads security
- Tool “delete_skill” rewrote its description, which is the text the model reads security
- Tool “fetch_answer” rewrote its description, which is the text the model reads security
- Tool “fetch_narada_result” rewrote its description, which is the text the model reads security
- Tool “get_author_profile” rewrote its description, which is the text the model reads security
- Tool “get_certificate” rewrote its description, which is the text the model reads security
- Tool “get_persona” rewrote its description, which is the text the model reads security
- Tool “get_persona_journal” rewrote its description, which is the text the model reads security
- Tool “get_skill” rewrote its description, which is the text the model reads security
- Tool “leave_comment” rewrote its description, which is the text the model reads security
- Tool “leave_message” rewrote its description, which is the text the model reads security
- Tool “list_blobs” rewrote its description, which is the text the model reads security
- Tool “list_collection” rewrote its description, which is the text the model reads security
- Tool “list_content” rewrote its description, which is the text the model reads security
- Tool “list_personas” rewrote its description, which is the text the model reads security
- Tool “list_provenance” rewrote its description, which is the text the model reads security
- Tool “list_skill_groups” rewrote its description, which is the text the model reads security
- Tool “list_skills” rewrote its description, which is the text the model reads security
- Tool “load_skill_group” rewrote its description, which is the text the model reads security
- Tool “mysloodsiewnia_get” rewrote its description, which is the text the model reads security
- Tool “mysloodsiewnia_list” rewrote its description, which is the text the model reads security
- Tool “mysloodsiewnia_search” rewrote its description, which is the text the model reads security
- Tool “mysloodsiewnia_status” rewrote its description, which is the text the model reads security
- Tool “read_blob” rewrote its description, which is the text the model reads security
- Tool “read_collection_item” rewrote its description, which is the text the model reads security
- Tool “read_content” rewrote its description, which is the text the model reads security
- Tool “read_provenance” rewrote its description, which is the text the model reads security
- Tool “recall” rewrote its description, which is the text the model reads security
- Tool “record_persona_reflection” rewrote its description, which is the text the model reads security
- Tool “remember” rewrote its description, which is the text the model reads security
- Tool “request_access” rewrote its description, which is the text the model reads security
- Tool “request_license” rewrote its description, which is the text the model reads security
- Tool “run_narada” rewrote its description, which is the text the model reads security
- Tool “submit_answer” rewrote its description, which is the text the model reads security
- Tool “suggest_skills” rewrote its description, which is the text the model reads security
- Tool “synthesise_persona_patterns” rewrote its description, which is the text the model reads security
- Tool “upsert_skill” rewrote its description, which is the text the model reads security
- Tool “verify_content” rewrote its description, which is the text the model reads security
- Tool coverage: 93% → 0% ▼ functional
- Schema quality: 155 → 104 ▲ functional
- MCP protocol: fail → pass ▲ functional
- The server now declares the “logging” capability functional
- Schema quality: excellent → good functional
- MCP protocol version: 2024-11-05 → 2026-07-28 functional
- “ask_human” reworded the description of “context” cosmetic
- “ask_human” reworded the description of “from” cosmetic
- “ask_human” reworded the description of “question” cosmetic
- “bootstrap_session” reworded the description of “code” cosmetic
- “fetch_answer” reworded the description of “id” cosmetic
- “fetch_narada_result” reworded the description of “id” cosmetic
- “get_certificate” reworded the description of “slug” cosmetic
- “get_persona” reworded the description of “slug” cosmetic
- “get_persona_journal” reworded the description of “slug” cosmetic
- “get_skill” reworded the description of “slug” cosmetic
- “leave_comment” reworded the description of “from” cosmetic
- “leave_comment” reworded the description of “slug” cosmetic
- “leave_comment” reworded the description of “text” cosmetic
- “leave_message” reworded the description of “contact” cosmetic
- “leave_message” reworded the description of “context” cosmetic
- “leave_message” reworded the description of “from” cosmetic
- “leave_message” reworded the description of “regarding” cosmetic
- “leave_message” reworded the description of “text” cosmetic
- “list_blobs” reworded the description of “blob_type” cosmetic
- “list_blobs” reworded the description of “caller_id” cosmetic
- “list_blobs” reworded the description of “caller_kind” cosmetic
- “list_content” reworded the description of “tag” cosmetic
- “list_content” reworded the description of “type” cosmetic
- “list_provenance” reworded the description of “slug” cosmetic
- “list_skills” reworded the description of “category” cosmetic
- “list_skills” reworded the description of “tag” cosmetic
- “load_skill_group” reworded the description of “name” cosmetic
- “mysloodsiewnia_get” reworded the description of “doc_slug” cosmetic
- “mysloodsiewnia_list” reworded the description of “doc_type” cosmetic
- “mysloodsiewnia_list” reworded the description of “limit” cosmetic
- “mysloodsiewnia_list” reworded the description of “offset” cosmetic
- “mysloodsiewnia_search” reworded the description of “doc_slug” cosmetic
- “mysloodsiewnia_search” reworded the description of “doc_type” cosmetic
- “mysloodsiewnia_search” reworded the description of “limit” cosmetic
- “mysloodsiewnia_search” reworded the description of “query” cosmetic
- “mysloodsiewnia_write” reworded the description of “body” cosmetic
- “mysloodsiewnia_write” reworded the description of “doc_type” cosmetic
- “mysloodsiewnia_write” reworded the description of “meta” cosmetic
- “mysloodsiewnia_write” reworded the description of “source_path” cosmetic
- “mysloodsiewnia_write” reworded the description of “title” cosmetic
- “read_blob” reworded the description of “caller_id” cosmetic
- “read_blob” reworded the description of “caller_kind” cosmetic
- “read_blob” reworded the description of “slug” cosmetic
- “read_collection_item” reworded the description of “slug” cosmetic
- “read_content” reworded the description of “slug” cosmetic
- “read_provenance” reworded the description of “id” cosmetic
- “read_provenance” reworded the description of “slug” cosmetic
- “recall” reworded the description of “code” cosmetic
- “recall” reworded the description of “limit” cosmetic
- “recall” reworded the description of “query” cosmetic
- “record_persona_reflection” reworded the description of “error_context” cosmetic
- “record_persona_reflection” reworded the description of “narada_id” cosmetic
- “record_persona_reflection” reworded the description of “persona_slug” cosmetic
- “remember” reworded the description of “code” cosmetic
- “remember” reworded the description of “from” cosmetic
- “remember” reworded the description of “tags” cosmetic
- “remember” reworded the description of “text” cosmetic
- “request_access” reworded the description of “slug” cosmetic
- “request_license” reworded the description of “caller_id” cosmetic
- “request_license” reworded the description of “intended_use” cosmetic
- “run_narada” reworded the description of “context” cosmetic
- “run_narada” reworded the description of “from” cosmetic
- “submit_answer” reworded the description of “answer” cosmetic
- “submit_answer” reworded the description of “slug” cosmetic
- “suggest_skills” reworded the description of “files” cosmetic
- “suggest_skills” reworded the description of “git_origin” cosmetic
- “suggest_skills” reworded the description of “languages” cosmetic
- “synthesise_persona_patterns” reworded the description of “slug” cosmetic
- “upsert_skill” reworded the description of “body” cosmetic
- “upsert_skill” reworded the description of “tags” cosmetic
- “verify_content” reworded the description of “slug” cosmetic
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://kapoost.humanmcp.net/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=kapoost.humanmcp.net | CN=YE1,O=Let's Encrypt,C=US | 29 Aug 2026 | 27 Nov 2026 | ECDSA 256 | ECDSA-SHA384 | 5be638412765aaf178f5843cd1adcbaa415 |
| SANs: kapoost.humanmcp.net | ||||||
| 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 kapoost.humanmcp.net. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| net. | present | 37331 | 13 | Verified |
| humanmcp.net. | 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 |
| Header | Value |
|---|---|
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://kapoost.humanmcp.net/mcp | Verified | 200 | |
| http (plaintext) | http://kapoost.humanmcp.net/mcp | HTTPS enforced | 301 | https://kapoost.humanmcp.net/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 →
about_humanmcp ~42
Self-description of this humanMCP server. Deterministic, no bootstrap required — call this first to decide whether the rest of the API is relevant.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
ask_human ~72
Submit an async question to kapoost. Returns an ID. Rate-limited 5/hr/IP. Poll fetch_answer later — kapoost answers on his own schedule (minutes, hours, or days).
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | – |
| from | string | – | – |
| question | string | yes | – |
No output schema declared.
No examples provided.
bootstrap_session ~48
Validate the Polish poetry session code, then emit the full team briefing (guardian + style + personas + skills + persist block). Rate-limited 5/min/IP.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
No output schema declared.
No examples provided.
delete_skill ~32
Delete a skill by slug. Owner-only: requires Authorization: Bearer <token>.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
fetch_answer ~47
Poll for an answer to an ask_human question. Marks the question as fetched the first time an answer is returned. Rate-limited 30/hr/IP.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
fetch_narada_result ~44
Poll a narada job by ID. Statuses: pending, running, done, failed. When done, returns all persona voices.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
get_author_profile ~26
Author identity, bio, and a browsing cheatsheet. Records a profile-view event.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_certificate ~27
Return a formatted copyright/authenticity certificate for a piece.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
get_persona ~85
Return one persona's full prompt by slug. Session-gated except for Hodor (guardian rules must always apply). Pass session_token if your client cannot set an Authorization header.
| Name | Type | Req | Description |
|---|---|---|---|
| session_token | string | – | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
| slug | string | yes | – |
No output schema declared.
No examples provided.
get_persona_journal ~42
Read a persona's raw reflection journal. Owner-only — the journal is a private feedback loop, not for external callers.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
get_skill ~84
Return one skill's full body by slug. Session-gated except for -public suffixed skills (guardian bypass). Pass session_token if your client cannot set an Authorization header.
| Name | Type | Req | Description |
|---|---|---|---|
| session_token | string | – | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
| slug | string | yes | – |
No output schema declared.
No examples provided.
leave_comment ~54
Attach a short comment (≤280 chars) to a piece kapoost has published. Truncated silently past the limit.
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | – | – |
| slug | string | yes | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
leave_message ~74
Send kapoost a longer message. context REQUIRED (why you're writing / which piece / which task). contact optional — without it no reply is possible.
| Name | Type | Req | Description |
|---|---|---|---|
| contact | string | – | – |
| context | string | yes | – |
| from | string | – | – |
| regarding | string | – | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
list_blobs ~67
List typed data artifacts (images, contact, vectors, documents, datasets, capsules). Filter by blob_type. Readable-column reflects caller_kind + caller_id vs audience.
| Name | Type | Req | Description |
|---|---|---|---|
| blob_type | string | – | – |
| caller_id | string | – | – |
| caller_kind | string | – | – |
No output schema declared.
No examples provided.
list_collection ~65
List works kapoost owns but did NOT create. Public items always; members-only surface only after session activation.
| Name | Type | Req | Description |
|---|---|---|---|
| session_token | string | – | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
No output schema declared.
No examples provided.
list_content ~41
List published pieces (slug, title, type, access, tags). Optional type/tag filters.
| Name | Type | Req | Description |
|---|---|---|---|
| tag | string | – | – |
| type | string | – | – |
No output schema declared.
No examples provided.
list_personas ~26
List every persona (slug, title, role). Full prompts unlock after bootstrap_session.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_provenance ~40
List provenance items (chain of custody, certificates, invoices) for an artwork slug. Tries piece then collection.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
list_skill_groups ~29
Index of every skill tag in use, with slugs per group. Public — no bootstrap required.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_skills ~40
List skills (slug, category, title, tags). Optional category / tag filters.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| tag | string | – | – |
No output schema declared.
No examples provided.
load_skill_group ~81
Bulk-fetch every skill tagged with the given group name. Respects the bootstrap gate per-skill: -public suffix bypasses, everything else needs session.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
| session_token | string | – | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
No output schema declared.
No examples provided.
mysloodsiewnia_get ~80
Fetch one document from kapoost's vault by slug. Requires Authorization: Bearer <edit token or friend token>. Friend tokens: vault-side filter enforces scope + access:private invisibility — an out-of-scope or private slug returns not_found. Vault offline ⇒ {status:offline}.
| Name | Type | Req | Description |
|---|---|---|---|
| doc_slug | string | yes | – |
No output schema declared.
No examples provided.
mysloodsiewnia_list ~137
Enumerate vault documents without FTS — for browsing by type or paginating. Requires Authorization: Bearer <edit token or friend token>. Friend tokens see only their scoped doc_types; access:private is invisible. Args: {doc_type?: string filter (note/pdf/literatura/calendar_event/...), limit?: int 1-200 default 50, offset?: int default 0}. Returns [{slug, title, doc_type, created_at, chunk_count}]. Vault offline ⇒ {status:offline}.
| Name | Type | Req | Description |
|---|---|---|---|
| doc_type | string | – | – |
| limit | integer | – | – |
| offset | integer | – | – |
No output schema declared.
No examples provided.
mysloodsiewnia_search ~122
Full-text search (BM25 over SQLite FTS5) on kapoost's local vault corpus. Requires Authorization: Bearer <edit token or friend token>. Friend tokens see only their scoped doc_types; access:private is invisible. Returns {status, results:[{source, type, body, doc_slug, title, page, citation}], summary}. Vault offline ⇒ {status:offline}.
| Name | Type | Req | Description |
|---|---|---|---|
| doc_slug | string | – | – |
| doc_type | string | – | – |
| limit | integer | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
mysloodsiewnia_status ~80
Read-only liveness probe on kapoost's local vault (mysłoodsiewnia). Returns {status: online|degraded|offline, last_seen, commit_sha, personas_updated_at, skills_updated_at}. Offline is a stable state — retry later, don't escalate. Requires Authorization: Bearer <edit token or friend token>.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
mysloodsiewnia_write ~289
Ingest a new document into kapoost's vault (wave 2). OWNER-ONLY — friend tokens receive {status:write_denied,reason:owner_only}. Args: {doc_type (required), title (required), body (required, ≤100 KiB), source_path?, meta?}. Requires Authorization: Bearer <owner token>. On Unauthorized: obtain the token by either (a) calling bootstrap_session(code=<owner poet fragment>) and reading SESSION_TOKEN from the response briefing (1h TTL, preferred for agents that already know the code), or (b) if you have shell access on kapoost's Mac, running `security find-generic-password -s humanmcp-edit-token -w` to fetch the persistent EDIT_TOKEN. Server-side vault auto-tags via:humanmcp-bridge; op_id is dedup key (idempotent retries safe). Delete is permanently unavailable. Envelopes: {status:online, op_id, result:{slug, created_at}}, {status:invalid_args}, {status:payload_too_large, limit, got}, {status:offline}, {status:vault_timeout}, {status:vault_error, error}.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | – |
| doc_type | string | yes | – |
| meta | object | – | – |
| source_path | string | – | – |
| title | string | yes | – |
No output schema declared.
No examples provided.
prepare_narada ~176
Offline narada: returns the panel plus each persona's ready-to-run SYSTEM/USER prompts so YOU run them as your own subagents, instead of the server generating voices. No LLM cost, no rate limit, nothing recorded — no narada ID and no journal feedback. Prefer this over run_narada when your subagents can read material the server cannot (a repository, local files) or when the server has no API key. Session-gated.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | – |
| personas | array | – | Optional. Explicit persona slugs (from list_personas). When present the keyword manifest is not used. Omit for automatic keyword routing. |
| session_token | string | – | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
No output schema declared.
No examples provided.
read_blob ~56
Read one blob by slug. Returns text or base64-encoded data. Access-gated by audience unless blob is public.
| Name | Type | Req | Description |
|---|---|---|---|
| caller_id | string | – | – |
| caller_kind | string | – | – |
| slug | string | yes | – |
No output schema declared.
No examples provided.
read_collection_item ~73
Full record for one collection item + dossier count. Access-gated: private is never visible, members needs session.
| Name | Type | Req | Description |
|---|---|---|---|
| session_token | string | – | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
| slug | string | yes | – |
No output schema declared.
No examples provided.
read_content ~32
Read a public piece by slug. Locked pieces return a hint pointing at request_access.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
read_provenance ~40
Return one provenance item with resolvable file URLs. slug + id required.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| slug | string | yes | – |
No output schema declared.
No examples provided.
recall ~85
List memories saved under the given code, optionally substring-filtered by query. Session-gated for symmetry with remember.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| limit | integer | – | – |
| query | string | – | – |
| session_token | string | – | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
No output schema declared.
No examples provided.
record_persona_reflection ~70
Ask a persona to write a lesson-for-self after a rolled-back narada recommendation. Appends to the persona's journal via Sonnet/Haiku. Owner-only.
| Name | Type | Req | Description |
|---|---|---|---|
| error_context | string | yes | – |
| narada_id | string | yes | – |
| persona_slug | string | yes | – |
No output schema declared.
No examples provided.
remember ~95
Persist a note under the given session code. Session-gated — bootstrap_session first. Callers sharing the code share the memory.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| from | string | – | – |
| session_token | string | – | Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header. |
| tags | array | – | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
request_access ~42
Get the gate details for a locked piece: challenge question, manual-review flow, time-lock countdown, payment terms, or trade rules.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
request_license ~60
Declare intended use of a piece, get licensing terms + audit-log entry. caller_id is REQUIRED (whitespace-only rejected — storyboard-pinned).
| Name | Type | Req | Description |
|---|---|---|---|
| caller_id | string | yes | – |
| intended_use | string | yes | – |
| slug | string | yes | – |
No output schema declared.
No examples provided.
run_narada ~154
Create an async narada job: server routes context to 3-5 personas via keyword manifest, then generates each voice via Sonnet 4.6 (Haiku 4.5 for journal recaps). Returns job ID for polling. Pass `personas` to pick the voices yourself and skip the router entirely — the router matches keywords only and cannot read a request to include or exclude someone written in the context.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | yes | – |
| from | string | – | – |
| personas | array | – | Optional. Explicit persona slugs (from list_personas) to consult. When present the keyword manifest is not used and these exact personas answer, in this order. Omit for automatic keyword routing. |
No output schema declared.
No examples provided.
submit_answer ~42
Submit an answer to a challenge-gated piece. Correct answer unlocks and returns the full body.
| Name | Type | Req | Description |
|---|---|---|---|
| answer | string | yes | – |
| slug | string | yes | – |
No output schema declared.
No examples provided.
suggest_skills ~74
Deterministic manifest→tag mapping. Given files + languages + git_origin, returns up to 8 skill slugs and up to 5 personas, each with the reason it fired. No LLM classification.
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | – | – |
| git_origin | string | – | – |
| languages | array | – | – |
No output schema declared.
No examples provided.
synthesise_persona_patterns ~45
Force-run Sonnet synthesis over a persona's raw journal, replacing the previous pattern set. Owner-only — paid + writes internal state.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
upsert_skill ~74
Create or replace a skill by slug. Owner-only: requires Authorization: Bearer <token>. Writes JSON to content/skills/<slug>.json.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | – |
| category | string | yes | – |
| slug | string | yes | – |
| tags | array | – | – |
| title | string | yes | – |
No output schema declared.
No examples provided.
verify_content ~31
Verify a piece's Ed25519 signature against the server's owner public key.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
What is the humanMCP — kapoost MCP server?
humanMCP — kapoost is an MCP server listed in the public MCP registry as io.github.kapoost/humanmcp. Personal MCP server for humans who create. Proof of authorship, license control. This page covers its hosted endpoint (https://kapoost.humanmcp.net/mcp).
Is the humanMCP — kapoost MCP server safe to use?
humanMCP — kapoost 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 humanMCP — kapoost MCP server expose?
humanMCP — kapoost exposes 42 tools: about_humanmcp, ask_human, bootstrap_session, delete_skill, fetch_answer, and 37 more. Their descriptions and schemas cost roughly 2,923 tokens of context every time the server is loaded.
Does the humanMCP — kapoost MCP server require authentication?
No. We connected to humanMCP — kapoost without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the humanMCP — kapoost MCP server still maintained?
humanMCP — kapoost 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.