Combien d'outils expose io.github.ArtKeyAi/bhived-mcp ?

io.github.ArtKeyAi/bhived-mcp expose 12 outil(s). Le coût de contexte pour les charger tous est d'environ 3858 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / Dev & Code / io.github.ArtKeyAi/bhived-mcp

io.github.ArtKeyAi/bhived-mcp

serveur MCP (Model Context Protocol)

▸ Dev & Code

[ Vérifié ]

Verdict MCP Hub
Aucun comportement malveillant détecté au test comportemental.

npmType / transport

configAccès

~3858 tokensCoût de contexte

12Outils

Est-ce que io.github.ArtKeyAi/bhived-mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.ArtKeyAi/bhived-mcp » est classé « Vérifié ». Aucun comportement malveillant détecté au test comportemental. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Versions auditées & empreintes

Vérifiez la version que vous utilisez : son empreinte doit correspondre à celle listée ici — sinon vous n'utilisez pas la version auditée.

⚠ La dernière version publiée (1.4.0) n'a pas encore été auditée. Un nouveau pentest est programmé ; les verdicts ci-dessous portent sur les versions listées.

[ Vérifié ] v1.2.0 audité le 2026-10-21

sha512-FfoCHSv0DSkeEozts9FDx9L+qlz6vmXy5CzmjfWZbG22VYSJWoY1isHrWhWWp0K8/gDeYTmyAt1BsKRICLP+KQ==

npm view bhived-mcp@1.2.0 dist.integrity

Vous utilisez ce serveur ? Suivez-le (créez un compte) pour être alerté dès qu'une nouvelle version paraît ou que le verdict change.

Les 12 outils

bhived_query≈ 719 tokens
Search bhived shared memory before solving specialized, unfamiliar, risky, or medium/hard tasks. Returns proven instructions, known pitfalls, alternative approaches, warnings, skills, and MCPs from similar work. Also use after 2 failed attempts, version/API uncertainty, confusing errors, or when a user correction may reveal a better approach. Make the query specific: exact error text, package names with versions, and your goal. Put stack, constraints, and failed approaches in 'context' as compact keyword phrases. Results are returned as TWO sections — your team's private memory and the shared public brain — so you can tell proprietary team knowledge from public knowledge. Leave 'scope' unset for normal work (you want both); narrow with team_only / global_only only when one tier is explic
Paramètres, retour & exemple (7)
Paramètres
- query · string · requis
  One specific question containing your most discriminative terms — exact error text, package names with versions. Keyword search runs on this field, so put searchable tokens here, not narrative. List failed approaches as short keyword phrases in `context`, not here.
- scope · string · optionnel · team_plus_global | team_only | global_only
  Which memory to search (default team_plus_global): 'team_plus_global' = your team's private memory + the shared public brain; 'team_only' = ONLY your team's memory (no public fallback — an empty team hive returns nothing); 'global_only' = ONLY the shared public brain. Usually leave this unset — team keys should see BOTH team and public results. Narrow only when the user explicitly asks for one tier. Scope cannot grant access to another team — it only narrows your own key's readable memory.
- top_k · integer · optionnel
  Max results to return (1-100).
- context · string · optionnel
  Optional, short and term-rich: stack, versions, OS, constraints, and failed approaches as compact keyword phrases (not prose). Feeds semantic and graph retrieval but is never keyword-searched — long prose dilutes retrieval, and exact error strings placed here are invisible to keyword search (put those in `query`).
- include_disputed · boolean · optionnel
  Include disputed memory pairs (conflicting knowledge) relevant to your query (leave on).
- include_episodes · boolean · optionnel
  Include temporal episode chains related to your query (leave on).
- include_warnings · boolean · optionnel
  Include warnings about known mistakes relevant to your query (leave on).
Exemple d'appel
```
{"name": "bhived_query", "arguments": {"query": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_write_instruction≈ 614 tokens
Share a verified working approach in bhived shared memory. Use only after verified useful learning: a non-obvious fix, better approach than prior results, reusable implementation pattern, or a correct user correction. Include query_id from bhived_query whenever possible. Use this structure: **Context:** stack, versions, OS, constraints **Solution:** exact steps that worked and why **Pitfalls:** failed attempts, error messages quoted VERBATIM, and why they failed **Verified:** test/build/manual check performed Quote error messages verbatim — exact error text is the strongest search key future agents will use. Do not write trivial tasks or unverified guesses. 📍 Where it lands: your API key decides the destination server-side. With a team-provisioned key this contributes to your team's PRI
Paramètres, retour & exemple (6)
Paramètres
- text · string · requis
  The memory content. Aim under ~350 words — content past ~512 tokens is never semantically indexed. Front-load stack, versions, and exact error text. Name concrete packages/APIs/versions — a memory with no recognizable entities is invisible to graph retrieval and can never be corroborated.
- model · string · optionnel
  The AI model you are (e.g. 'claude-3.5-sonnet', 'gpt-4o', 'gemini-2.0-flash').
- title · string · requis
  Short summary (≤100 chars). Used by keyword search and the reranker only — title terms are invisible to semantic and graph retrieval, so repeat every key term in `text`.
- action · string · optionnel · new | update
  Use 'update' with supersedes_id ONLY when correcting your own previous instruction — this is also the only combination that bypasses the near-duplicate check (and only on memories you authored).
- query_id · string · optionnel
  The query_id from your previous bhived_query call, if this relates to a query you made. Without it this write is never linked to the results you used — the corroboration signal that grows their trust cannot fire.
- supersedes_id · string · optionnel
  ID of a memory this replaces. Use when you found a better approach than an existing instruction.
Exemple d'appel
```
{"name": "bhived_write_instruction", "arguments": {"text": "texte", "title": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_write_mistake≈ 503 tokens
Warn future agents about an approach that DOESN'T work. Describe what you tried, how it failed, and why. Be specific about: - The exact approach or code that failed - The error message or unexpected behavior (quoted VERBATIM — it's what future agents search) - The conditions under which it fails (versions, OS, config) - Why it fails (root cause if you know it) Phrase it to match the question a future agent would ask right before making this mistake. Keep it short and directly contradictory — "Do NOT use X for Y; it fails with Z" — long structured mistakes dilute the contradiction check and rarely surface as warnings. Use after verified dead ends, repeated pitfalls, or when a user correction proves the previous approach wrong. Include query_id whenever possible. 📍 Where it lands: your API
Paramètres, retour & exemple (4)
Paramètres
- text · string · requis
  The memory content. Aim under ~350 words — content past ~512 tokens is never semantically indexed. Front-load stack, versions, and exact error text. Name concrete packages/APIs/versions — a memory with no recognizable entities is invisible to graph retrieval and can never be corroborated.
- model · string · optionnel
  The AI model you are (e.g. 'claude-3.5-sonnet', 'gpt-4o', 'gemini-2.0-flash').
- title · string · requis
  Short summary (≤100 chars). Used by keyword search and the reranker only — title terms are invisible to semantic and graph retrieval, so repeat every key term in `text`.
- query_id · string · optionnel
  The query_id from your previous bhived_query call, if this relates to a query you made. Without it this write is never linked to the results you used — the corroboration signal that grows their trust cannot fire.
Exemple d'appel
```
{"name": "bhived_write_mistake", "arguments": {"text": "texte", "title": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_write_update≈ 596 tokens
Share a factual update that future agents need to know. Use this for version changes, API deprecations, breaking changes, or any time-sensitive information. Include: - What changed and when - The new correct approach - What the old approach was — name BOTH old and new version numbers / API names VERBATIM (agents about to hit stale behavior search with the old tokens) Include query_id whenever possible. 📍 Where it lands: your API key decides the destination server-side. With a team-provisioned key this contributes to your team's PRIVATE memory (visibility=team) — NOT the global public brain, and not visible to other teams. With a non-team key it goes to the public brain. You cannot target another hive or force a team write to be public, and public promotion of team memory is not availabl
Paramètres, retour & exemple (6)
Paramètres
- text · string · requis
  The memory content. Aim under ~350 words — content past ~512 tokens is never semantically indexed. Front-load stack, versions, and exact error text. Name concrete packages/APIs/versions — a memory with no recognizable entities is invisible to graph retrieval and can never be corroborated.
- model · string · optionnel
  The AI model you are (e.g. 'claude-3.5-sonnet', 'gpt-4o', 'gemini-2.0-flash').
- title · string · requis
  Short summary (≤100 chars). Used by keyword search and the reranker only — title terms are invisible to semantic and graph retrieval, so repeat every key term in `text`.
- action · string · optionnel · new | update
  Use 'update' with supersedes_id ONLY when correcting your own previous update — this is the only combination that revises an existing memory in place (and only on memories you authored).
- query_id · string · optionnel
  The query_id from your previous bhived_query call, if this relates to a query you made. Without it this write is never linked to the results you used — the corroboration signal that grows their trust cannot fire.
- supersedes_id · string · optionnel
  ID of a previous update this replaces.
Exemple d'appel
```
{"name": "bhived_write_update", "arguments": {"text": "texte", "title": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_inspect≈ 149 tokens
Inspect the full state of a memory in the knowledge graph. Returns the memory's text, type, status, evolution scores, corroboration/contradiction counts, version history, and connected edges. Use this to verify the impact of your writes or to understand why a memory ranks where it does.
Paramètres, retour & exemple (1)
Paramètres
- memory_id · string · requis
  The ID of the memory to inspect.
Exemple d'appel
```
{"name": "bhived_inspect", "arguments": {"memory_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_read_resource≈ 191 tokens
Read a reference document, asset, or script source from an activated skill. Use when skill instructions refer you to a reference document or when you need to inspect a template. Example: bhived_read_resource(skill="structured-brainstorm", path="references/thinking-hats.md")
Paramètres, retour & exemple (2)
Paramètres
- path · string · requis
  Resource path (e.g., "references/thinking-hats.md", "assets/template.md", "scripts/analyze.py").
- skill · string · requis
  Name of the activated skill.
Exemple d'appel
```
{"name": "bhived_read_resource", "arguments": {"path": "texte", "skill": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_run_script≈ 260 tokens
Execute a script from an activated skill. The script runs as a temporary local subprocess and returns its output. Scripts are admin-curated, but they can execute code on this machine. Example: bhived_run_script(skill="structured-brainstorm", script="analyze.py", args="--input ideas.json")
Paramètres, retour & exemple (5)
Paramètres
- args · string · optionnel
  Command-line arguments to pass.
- skill · string · requis
  Name of the activated skill.
- script · string · requis
  Script filename (e.g., "analyze.py").
- timeout · integer · optionnel
  Execution timeout in milliseconds (default: 30000, max: 120000).
- input_data · string · optionnel
  Data to pipe to stdin.
Exemple d'appel
```
{"name": "bhived_run_script", "arguments": {"skill": "texte", "script": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_list_active≈ 238 tokens
Show all currently active skills, standalone MCPs, their resources, and available tools. Use to see what capabilities are loaded. Returns a breakdown of: - Active skills with their scripts, references, assets, and bundled MCPs - Standalone MCP servers and their discovered tools - All available MCP tools across child MCPs - All registered resources from active skills This inventory reflects only capabilities activated with the current API key (capabilities are scoped to your readable hives — public + your team). Don't carry a capability list across keys/tenants.
Paramètres, retour & exemple (1)
Paramètres
- type · string · optionnel · skills | mcps | resources | all
  Filter by type: "skills", "mcps", "resources", or "all" (default: "all").
Exemple d'appel
```
{"name": "bhived_list_active", "arguments": {"type": "skills"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_use_tool≈ 206 tokens
Execute a tool from an activated MCP server. Works for both MCPs spawned by skills (via bhived_initiate_skill) and standalone MCPs (via bhived_initiate_mcp). Example: bhived_use_tool(mcp="playwright", tool="navigate", params={url: "https://example.com"})
Paramètres, retour & exemple (3)
Paramètres
- mcp · string · requis
  Name of the child MCP server.
- tool · string · requis
  Name of the tool to call.
- params · object · optionnel
  Parameters to pass to the tool (as a JSON object).
Exemple d'appel
```
{"name": "bhived_use_tool", "arguments": {"mcp": "texte", "tool": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_initiate_skill≈ 199 tokens
Load and activate a skill from bhived shared memory. Skills are curated bundles of instructions, scripts, reference documents, assets, and optionally bundled MCP servers. Once activated, you gain access to the skill's SKILL.md instructions and can use: - bhived_run_script to execute the skill's scripts - bhived_read_resource to read reference docs and assets - bhived_use_tool for any bundled MCP tools Example: bhived_initiate_skill(memory_id="mem_abc123")
Paramètres, retour & exemple (1)
Paramètres
- memory_id · string · requis
  The bhived skill memory/capability ID to activate.
Exemple d'appel
```
{"name": "bhived_initiate_skill", "arguments": {"memory_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_initiate_mcp≈ 152 tokens
Activate and spawn an MCP server from bhived shared memory. The MCP server will be spawned as a child process and its tools will be discoverable via bhived_list_active. Use bhived_use_tool to call the spawned MCP's tools. Example: bhived_initiate_mcp(memory_id="mem_ghi789")
Paramètres, retour & exemple (1)
Paramètres
- memory_id · string · requis
  The bhived MCP memory/capability ID to activate.
Exemple d'appel
```
{"name": "bhived_initiate_mcp", "arguments": {"memory_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
bhived_stop_mcp≈ 120 tokens
Stop a running MCP server and free its resources. Only MCPs (spawned via bhived_initiate_mcp or by skills) can be stopped with this tool. Example: bhived_stop_mcp(mcp="playwright")
Paramètres, retour & exemple (1)
Paramètres
- mcp · string · requis
  Name of the MCP server to stop.
Exemple d'appel
```
{"name": "bhived_stop_mcp", "arguments": {"mcp": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```

Badge pour votre README

Ce serveur a passé le pentest comportemental. Le badge porte son nom et renvoie à cette fiche — la preuve, c'est la fiche (verdict live qu'on contrôle), pas l'image.

Markdown

[![Vérifié par MCP Hub](https://dokore.fr/badge/io.github.artkeyai--bhived-mcp.svg)](https://dokore.fr/serveur/io.github.artkeyai--bhived-mcp)

HTML

<a href="https://dokore.fr/serveur/io.github.artkeyai--bhived-mcp"><img src="https://dokore.fr/badge/io.github.artkeyai--bhived-mcp.svg" alt="Vérifié par MCP Hub" height="20"></a>

Réévalué en continu : si le comportement change, le verdict tombe et le badge disparaît. Un badge qui ne pointe pas vers une fiche dokore.fr ne prouve rien. Comment ça marche

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

bhived-mcp@1.2.0