humanMCP — kapoost
Personal MCP server for humans who create. Proof of authorship, license control.
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'read_provenance' description lacks action verbin read_provenance
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"humanmcp": {
"url": "https://kapoost-humanmcp.fly.dev/mcp"
}
}
}Remote endpoints
https://kapoost-humanmcp.fly.dev/mcpstreamable-httphttps://kapoost.humanmcp.net/mcpstreamable-httpWhat it can do
Tool inventory
Tools (43)
⚪about_humanmcp
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
{
"type": "object",
"properties": {}
}🟡ask_human(question, context, from)
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). ALWAYS set `from` to a stable name for yourself: with it, sending the same question again returns the answer instead of creating a duplicate, which is the reliable path when your runtime cannot keep the ID between sessions.
Input Schema
{
"type": "object",
"properties": {
"question": {
"type": "string"
},
"context": {
"type": "string"
},
"from": {
"type": "string"
}
},
"required": [
"question"
]
}⚪bootstrap_session(code)
Validate the Polish poetry session code, then emit the full team briefing (guardian + style + personas + skills + persist block). Rate-limited 5/min/IP.
Input Schema
{
"type": "object",
"properties": {
"code": {
"type": "string"
}
},
"required": [
"code"
]
}🔴delete_skill(slug)
Delete a skill by slug. Owner-only: requires Authorization: Bearer <token>.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
]
}🟢fetch_answer(id)
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.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
]
}🟢fetch_narada_result(id)
Poll a narada job by ID. Statuses: pending, running, done, failed. When done, returns all persona voices.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
]
}🟢get_author_profile
Author identity, bio, and a browsing cheatsheet. Records a profile-view event.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_certificate(slug)
Return a formatted copyright/authenticity certificate for a piece.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
]
}🟡get_persona(slug, session_token)
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.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"session_token": {
"type": "string",
"description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header."
}
},
"required": [
"slug"
]
}🟢get_persona_journal(slug)
Read a persona's raw reflection journal. Owner-only — the journal is a private feedback loop, not for external callers.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
]
}🟡get_skill(slug, session_token)
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.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"session_token": {
"type": "string",
"description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header."
}
},
"required": [
"slug"
]
}⚪leave_comment(slug, text, from)
Attach a short comment (≤280 chars) to a piece kapoost has published. Truncated silently past the limit.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"text": {
"type": "string"
},
"from": {
"type": "string"
}
},
"required": [
"slug",
"text"
]
}🟡leave_message(text, context, contact, from, regarding)
Send kapoost a longer message. context REQUIRED (why you're writing / which piece / which task). contact optional — without it no reply is possible.
Input Schema
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"context": {
"type": "string"
},
"contact": {
"type": "string"
},
"from": {
"type": "string"
},
"regarding": {
"type": "string"
}
},
"required": [
"text",
"context"
]
}🟢list_blobs(blob_type, caller_kind, caller_id)
List typed data artifacts (images, contact, vectors, documents, datasets, capsules). Filter by blob_type. Readable-column reflects caller_kind + caller_id vs audience.
Input Schema
{
"type": "object",
"properties": {
"blob_type": {
"type": "string"
},
"caller_kind": {
"type": "string"
},
"caller_id": {
"type": "string"
}
}
}🟢list_collection(session_token)
List works kapoost owns but did NOT create. Public items always; members-only surface only after session activation.
Input Schema
{
"type": "object",
"properties": {
"session_token": {
"type": "string",
"description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header."
}
}
}🟢list_content(type, tag)
List published pieces (slug, title, type, access, tags). Optional type/tag filters.
Input Schema
{
"type": "object",
"properties": {
"type": {
"type": "string"
},
"tag": {
"type": "string"
}
}
}🟢list_personas
List every persona (slug, title, role). Full prompts unlock after bootstrap_session.
Input Schema
{
"type": "object",
"properties": {}
}🟢list_provenance(slug)
List provenance items (chain of custody, certificates, invoices) for an artwork slug. Tries piece then collection.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
]
}🟢list_skill_groups
Index of every skill tag in use, with slugs per group. Public — no bootstrap required.
Input Schema
{
"type": "object",
"properties": {}
}🟢list_skills(category, tag)
List skills (slug, category, title, tags). Optional category / tag filters.
Input Schema
{
"type": "object",
"properties": {
"category": {
"type": "string"
},
"tag": {
"type": "string"
}
}
}🟢load_skill_group(name, session_token)
Bulk-fetch every skill tagged with the given group name. Respects the bootstrap gate per-skill: -public suffix bypasses, everything else needs session.
Input Schema
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"session_token": {
"type": "string",
"description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header."
}
},
"required": [
"name"
]
}🟢mysloodsiewnia_get(doc_slug)
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}.
Input Schema
{
"type": "object",
"properties": {
"doc_slug": {
"type": "string"
}
},
"required": [
"doc_slug"
]
}🟢mysloodsiewnia_list(doc_type, limit, offset)
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}.
Input Schema
{
"type": "object",
"properties": {
"doc_type": {
"type": "string"
},
"limit": {
"type": "integer"
},
"offset": {
"type": "integer"
}
}
}🟢mysloodsiewnia_search(query, limit, doc_type, doc_slug)
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}.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"limit": {
"type": "integer"
},
"doc_type": {
"type": "string"
},
"doc_slug": {
"type": "string"
}
},
"required": [
"query"
]
}🟢mysloodsiewnia_status
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
{
"type": "object",
"properties": {}
}🔴mysloodsiewnia_write(doc_type, title, body, source_path, meta)
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}.
Input Schema
{
"type": "object",
"properties": {
"doc_type": {
"type": "string"
},
"title": {
"type": "string"
},
"body": {
"type": "string"
},
"source_path": {
"type": "string"
},
"meta": {
"type": "object"
}
},
"required": [
"doc_type",
"title",
"body"
]
}🟢prepare_narada(context, personas, session_token)
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.
Input Schema
{
"type": "object",
"properties": {
"context": {
"type": "string"
},
"personas": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional. Explicit persona slugs (from list_personas). When present the keyword manifest is not used. Omit for automatic keyword routing."
},
"session_token": {
"type": "string",
"description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header."
}
},
"required": [
"context"
]
}🟢read_blob(slug, caller_kind, caller_id)
Read one blob by slug. Returns text or base64-encoded data. Access-gated by audience unless blob is public.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"caller_kind": {
"type": "string"
},
"caller_id": {
"type": "string"
}
},
"required": [
"slug"
]
}🟢read_collection_item(slug, session_token)
Full record for one collection item + dossier count. Access-gated: private is never visible, members needs session.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"session_token": {
"type": "string",
"description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header."
}
},
"required": [
"slug"
]
}🟢read_content(slug)
Read a public piece by slug. Locked pieces return a hint pointing at request_access.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
]
}🟢read_provenance(slug, id)
Return one provenance item with resolvable file URLs. slug + id required.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"id": {
"type": "string"
}
},
"required": [
"slug",
"id"
]
}🟢recall(code, query, limit, session_token)
List memories saved under the given code, optionally substring-filtered by query. Session-gated for symmetry with remember.
Input Schema
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"query": {
"type": "string"
},
"limit": {
"type": "integer"
},
"session_token": {
"type": "string",
"description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header."
}
},
"required": [
"code"
]
}🟡record_persona_reflection(narada_id, persona_slug, error_context)
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.
Input Schema
{
"type": "object",
"properties": {
"narada_id": {
"type": "string"
},
"persona_slug": {
"type": "string"
},
"error_context": {
"type": "string"
}
},
"required": [
"narada_id",
"persona_slug",
"error_context"
]
}⚪remember(text, code, from, tags, session_token)
Persist a note under the given session code. Session-gated — bootstrap_session first. Callers sharing the code share the memory.
Input Schema
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"code": {
"type": "string"
},
"from": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"session_token": {
"type": "string",
"description": "Optional. The SESSION_TOKEN emitted by bootstrap_session. Pass it here when your client cannot set a per-call Authorization: Bearer header."
}
},
"required": [
"text",
"code"
]
}🟢request_access(slug)
Get the gate details for a locked piece: challenge question, manual-review flow, time-lock countdown, payment terms, or trade rules.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
]
}🟢request_license(slug, intended_use, caller_id)
Declare intended use of a piece, get licensing terms + audit-log entry. caller_id is REQUIRED (whitespace-only rejected — storyboard-pinned).
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"intended_use": {
"type": "string"
},
"caller_id": {
"type": "string"
}
},
"required": [
"slug",
"intended_use",
"caller_id"
]
}🟡run_narada(context, from, personas)
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.
Input Schema
{
"type": "object",
"properties": {
"context": {
"type": "string"
},
"from": {
"type": "string"
},
"personas": {
"type": "array",
"items": {
"type": "string"
},
"description": "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."
}
},
"required": [
"context"
]
}🟢search_content(query, limit)
Search kapoost's pieces by words in title, tags, description and body. Every word must match (AND). Polish diacritics are folded, so "czlowieczenstwa" finds "człowieczeństwa". Use this BEFORE ask_human — most questions about which piece is which are answered here instantly, while ask_human waits for a human. Locked pieces are matched by title and tags only; their body is never searched or quoted.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"limit": {
"type": "integer"
}
},
"required": [
"query"
]
}🟡submit_answer(slug, answer)
Submit an answer to a challenge-gated piece. Correct answer unlocks and returns the full body.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"answer": {
"type": "string"
}
},
"required": [
"slug",
"answer"
]
}⚪suggest_skills(files, languages, git_origin)
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.
Input Schema
{
"type": "object",
"properties": {
"files": {
"type": "array",
"items": {
"type": "string"
}
},
"languages": {
"type": "array",
"items": {
"type": "string"
}
},
"git_origin": {
"type": "string"
}
}
}⚪synthesise_persona_patterns(slug)
Force-run Sonnet synthesis over a persona's raw journal, replacing the previous pattern set. Owner-only — paid + writes internal state.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
]
}🟡upsert_skill(slug, category, title, body, tags)
Create or replace a skill by slug. Owner-only: requires Authorization: Bearer <token>. Writes JSON to content/skills/<slug>.json.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"category": {
"type": "string"
},
"title": {
"type": "string"
},
"body": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"slug",
"category",
"title",
"body"
]
}⚪verify_content(slug)
Verify a piece's Ed25519 signature against the server's owner public key.
Input Schema
{
"type": "object",
"properties": {
"slug": {
"type": "string"
}
},
"required": [
"slug"
]
}Community
Evidence