Several models from different labs plan in a blind proposal, debate and review loop. Your own keys.
Inferido de los transportes que declara este listado (stdio). Que un cliente no aparezca aquí no significa que se haya descartado: simplemente Forge no puede confirmarlo.
ANTHROPIC_API_KEYClave de APIopcionalYour own Anthropic API key. Needed only by chains that seat Anthropic models.
OPENAI_API_KEYClave de APIopcionalYour own OpenAI API key. Needed only by chains that seat OpenAI models.
GOOGLE_API_KEYClave de APIopcionalYour own Google (Gemini) API key. Needed only by chains that seat Google (Gemini) models.
MISTRAL_API_KEYClave de APIopcionalYour own Mistral API key. Needed only by chains that seat Mistral models.
DEEPSEEK_API_KEYClave de APIopcionalYour own DeepSeek API key. Needed only by chains that seat DeepSeek models.
GROQ_API_KEYClave de APIopcionalYour own Groq API key. Needed only by chains that seat Groq models.
TOGETHER_API_KEYClave de APIopcionalYour own Together API key. Needed only by chains that seat Together models.
COHERE_API_KEYClave de APIopcionalYour own Cohere API key. Needed only by chains that seat Cohere models.
OPENROUTER_API_KEYClave de APIopcionalYour own OpenRouter API key. Needed only by chains that seat OpenRouter models.
ZAI_API_KEYClave de APIopcionalYour own Z.ai API key. Needed only by chains that seat Z.ai models.
Declarado por el autor en el registro oficial de MCP. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
La verificación confirma la identidad del publicador (la propiedad del repo), no la seguridad del código. El análisis de seguridad cubre los CVE conocidos y los scripts de instalación sospechosos.
Leído del código que npm publica realmente, en el momento del análisis. El paquete nunca se ejecutó. Las herramientas registradas dinámicamente en tiempo de ejecución, o escondidas en código empaquetado o minificado, pueden pasarse por alto — así que esto es un mínimo de la superficie de herramientas, no un censo completo.
my-first-chainA minimal real chain: one builder, one critic, one round.A minimal real chain: one builder, one critic, one round.
No se publicó ningún esquema de entrada para esta herramienta.
list_chainsChains available to run, with their description and worst-case price from a dry run.Chains available to run, with their description and worst-case price from a dry run.
No se publicó ningún esquema de entrada para esta herramienta.
dry_runPrice a chain without calling any model. chain is a chain name as list_chains shows it, never a path. json: true returns one JSON document instead of text: the floor and worst-case price, every row, and which seat lacks which API key.Price a chain without calling any model. chain is a chain name as list_chains shows it, never a path. json: true returns one JSON document instead of text: the floor and worst-case price, every row, and which seat lacks which API key.
No se publicó ningún esquema de entrada para esta herramienta.
start_runStart a harness run in the background. Returns the run id to poll with run_status, or started:false with the exit code and log tail if the run stopped at once. chain is a chain name as list_chains shows it (never a path). task, draft, context and from_run are paths inside your working directory (ta…Start a harness run in the background. Returns the run id to poll with run_status, or started:false with the exit code and log tail if the run stopped at once. chain is a chain name as list_chains shows it (never a path). task, draft, context and from_run are paths inside your working directory (ta…
No se publicó ningún esquema de entrada para esta herramienta.
external_promptWhen a run is paused at an external seat: the exact system and user prompt that stage needs answered. A run can wait on several stages at once (e.g. a panel of external critics): `waiting` lists them all; pass stage to get another one's prompt. Answer each with submit_stage; the run resumes once no…When a run is paused at an external seat: the exact system and user prompt that stage needs answered. A run can wait on several stages at once (e.g. a panel of external critics): `waiting` lists them all; pass stage to get another one's prompt. Answer each with submit_stage; the run resumes once no…
No se publicó ningún esquema de entrada para esta herramienta.
prepare_stage_promptFor a run paused at an external seat: write stage_prompt.md, a self-contained bundle a fresh subagent can act on with zero prior context, so a driving session can dispatch the stage instead of authoring it inline. Fork a subagent, give it only this file's path; take its returned deliverable back to…For a run paused at an external seat: write stage_prompt.md, a self-contained bundle a fresh subagent can act on with zero prior context, so a driving session can dispatch the stage instead of authoring it inline. Fork a subagent, give it only this file's path; take its returned deliverable back to…
No se publicó ningún esquema de entrada para esta herramienta.
submit_stageWrite the answer for an external stage into the run folder, then resume the run in the background. The stage must be one external_prompt lists under `waiting`; the run resumes once all of them are answered. claimed_by is optional (v3 §1): a self-declared peer-session name, recorded as this stage's…Write the answer for an external stage into the run folder, then resume the run in the background. The stage must be one external_prompt lists under `waiting`; the run resumes once all of them are answered. claimed_by is optional (v3 §1): a self-declared peer-session name, recorded as this stage's…
No se publicó ningún esquema de entrada para esta herramienta.
resume_runResume a paused run after its external stage was answered (submit_stage does this for you), or a run stopped by the spend cap (pass a higher max_usd). Completed stages replay from disk and cost nothing.Resume a paused run after its external stage was answered (submit_stage does this for you), or a run stopped by the spend cap (pass a higher max_usd). Completed stages replay from disk and cost nothing.
No se publicó ningún esquema de entrada para esta herramienta.
spend_reportWhat every run has cost across a window of days, not just one run. Derived from the run folders on disk - nothing is recorded anywhere else and nothing leaves this machine. Use this to answer "what have I spent today" before starting another run.What every run has cost across a window of days, not just one run. Derived from the run folders on disk - nothing is recorded anywhere else and nothing leaves this machine. Use this to answer "what have I spent today" before starting another run.
No se publicó ningún esquema de entrada para esta herramienta.
verdict_statsSin descripción publicadaEsta herramienta no publicó ninguna descripción. Forge no se la inventa.
metrics_reportDESCRIPTIVE TELEMETRY ONLY, not an evaluation, benchmark or baseline: amendment rate, withdrawal rate, objection-follow-through rate, and tool-call usage, derived from existing run logs (report.json and HANDOFF.md) on disk across a window of days. This is the zero-cost substitute for a cut evaluati…DESCRIPTIVE TELEMETRY ONLY, not an evaluation, benchmark or baseline: amendment rate, withdrawal rate, objection-follow-through rate, and tool-call usage, derived from existing run logs (report.json and HANDOFF.md) on disk across a window of days. This is the zero-cost substitute for a cut evaluati…
No se publicó ningún esquema de entrada para esta herramienta.
list_runsRuns on disk, newest first, with state and cost.Runs on disk, newest first, with state and cost.
No se publicó ningún esquema de entrada para esta herramienta.
run_statusState of one run: stage reached, panel verdicts, scoreboard, files produced, cost. Pass brief=true for a short, regenerated-on-demand resume brief instead - what a returning session with fresh context needs to re-enter the run.State of one run: stage reached, panel verdicts, scoreboard, files produced, cost. Pass brief=true for a short, regenerated-on-demand resume brief instead - what a returning session with fresh context needs to re-enter the run.
No se publicó ningún esquema de entrada para esta herramienta.
read_run_fileRead a file from a run folder (deliverable.md, BOARD.md, HANDOFF.md, proposals.md, build.md, revise-1.md, panel-1-<lab>.md, run.log, report.json; report-partial.json for a run the spend cap stopped).Read a file from a run folder (deliverable.md, BOARD.md, HANDOFF.md, proposals.md, build.md, revise-1.md, panel-1-<lab>.md, run.log, report.json; report-partial.json for a run the spend cap stopped).
No se publicó ningún esquema de entrada para esta herramienta.
plan_outlineSection tree of a run's deliverable (or any markdown file) with word counts and the build-volume heuristic, plus the scope ledger if present.Section tree of a run's deliverable (or any markdown file) with word counts and the build-volume heuristic, plus the scope ledger if present.
No se publicó ningún esquema de entrada para esta herramienta.
write_taskprivilegiadaWrite or overwrite a task file under tasks/ (the request the harness plans against).Write or overwrite a task file under tasks/ (the request the harness plans against).
No se publicó ningún esquema de entrada para esta herramienta.
15 de 16 herramientas publicaron una descripción.
Los nombres y descripciones de las herramientas los escribe el publicador y se muestran literalmente como texto inerte. Son las cadenas que un cliente MCP pasa al modelo, así que Forge las analiza en busca de patrones de inyección de prompts — cualquier hallazgo aparece junto al análisis de seguridad de arriba. «Privilegiada» es una coincidencia de palabra clave en el nombre de la herramienta, no una auditoría de lo que hace: un nombre inofensivo puede hacer cualquier cosa.
Several models from different labs plan in a blind proposal, debate and review loop. Your own keys.
Los nombres enlazados abren el índice de Forge con todas las entradas que se observó que exponen esa herramienta. Ver todas las herramientas indexadas.
El rastreo se detuvo en el límite de profundidad 4. Nada por debajo de ese nivel llegó a resolverse.
El rastreo se detuvo en el límite de 60 paquetes. El resto del árbol nunca se resolvió.
Hay 36 paquetes resueltos más que no se dibujan aquí (límite de visualización: 24). Toda dependencia con avisos de seguridad se dibuja aunque se supere el límite. Inventario completo (SBOM CycloneDX)
53 dependencias declaradas nunca llegaron al árbol. Faltan en la resolución de Forge, no en el paquete.
+41 más sin listar. Los recuentos por motivo de arriba las incluyen todas.
No se siguen: peerDependencies. Este árbol cubre solo dependencias en tiempo de ejecución, así que lo que estas arrastren nunca se resolvió.