此 MCP 可以做什么
Stores and retrieves isolated bi-temporal agent memories, embeddings, summaries, verification results, and signed records through paid x402 services.
功能
工具
15
工具
agora_catalog
FREE. Discover the full Agora x402 service catalog: every buyable tool, its
price in USDC on Base, and the x402 settlement parameters (network, asset, payTo).
Call this first to see what you can buy and how to pay.
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
code_review
PAID (0.05 USDC). Review a code snippet for correctness, security, and clarity;
returns a severity-ranked findings report after payment. Returns an x402 quote.
输入模式
{'type': 'object', 'required': ['code'], 'properties': {'code': {'type': 'string', 'description': 'The source code to review.'}, 'language': {'type': 'string', 'default': 'auto', 'description': "Programming language (or 'auto' to detect)."}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
embed_batch
PAID (0.005 USDC). Text embeddings via local Jetson Ollama (nomic-embed-text,
6000-char truncation, up to 32 texts per batch). Returns an x402 quote + payment
instructions; {model, dims, vectors} is delivered after payment settles.
输入模式
{'type': 'object', 'required': ['texts'], 'properties': {'texts': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of strings to embed (max 32).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
fact_verify
PAID (0.25 USDC). Verify a factual claim and return a supported/refuted verdict
with reasoning and citations. Returns an x402 quote + payment instructions.
输入模式
{'type': 'object', 'required': ['claim'], 'properties': {'claim': {'type': 'string', 'description': 'The claim to verify.'}, 'sources': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Optional list of source URLs/texts to check against.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
mnemos_as_of
PAID (0.005 USDC). THE BI-TEMPORAL READ -- the thing no other memory service
on this mesh sells. Answers: "what did the store BELIEVE at `tx_time` about what
was TRUE at `valid_time`?" Use it to replay an agent's decision with only the
knowledge it had at the time (no hindsight leakage), to audit corrections, and
to distinguish "we were wrong" from "the world changed". Returns an x402 quote.
输入模式
{'type': 'object', 'properties': {'k': {'type': 'integer', 'default': 5, 'description': 'Number of results (max 25).'}, 'key': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Exact key to look up (or use `query`).'}, 'query': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Semantic query (or use `key`).'}, 'tx_time': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO8601 -- point on the SYSTEM-BELIEF axis. Defaults to now.'}, 'valid_time': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO8601 -- point on the WORLD-TRUTH axis. Defaults to now.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
mnemos_get_context
PAID (0.005 USDC). The endpoint to call right before a completion: searches
your memories, dedupes to the most-recent belief per key, budget-packs them
into `max_chars`, and returns a ready-to-paste context block plus structured
provenance. Content flagged as prompt-injection is excluded from the block.
Optionally assembled AS OF a past time. Returns an x402 quote.
输入模式
{'type': 'object', 'required': ['query'], 'properties': {'k': {'type': 'integer', 'default': 8, 'description': 'Max memories to consider (max 25).'}, 'as_of': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO8601 -- assemble context as it stood at this time.'}, 'query': {'type': 'string', 'description': 'What the upcoming completion is about.'}, 'max_chars': {'type': 'integer', 'default': 4000, 'description': 'Character budget for the assembled block.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
mnemos_provision
PAID (0.50 USDC, monthly floor). Mint your own fully isolated bi-temporal
memory namespace. Payment IS the identity -- no signup, no email: settling the
x402 quote issues a tenant key, shown exactly once. Returns an x402 quote.
输入模式
{'type': 'object', 'properties': {'label': {'type': 'string', 'default': 'unnamed', 'description': "A human label for your tenant (e.g. your agent's name)."}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
mnemos_saas_info
FREE. Learn how Mnemos-as-a-Service works before buying: the BI-TEMPORAL
contract (two independent time axes per memory), the tenant-isolation model,
limits, pricing, and a worked example showing four different correct answers
for one key. No payment, no tenant data. Call this first.
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
mnemos_search
PAID (0.005 USDC). Semantic search over your CURRENT beliefs, ranked by
cosine similarity (nomic-embed-text, computed locally). Raw embedding vectors
are never returned. Returns an x402 quote; send X-TENANT-KEY once settled.
输入模式
{'type': 'object', 'required': ['query'], 'properties': {'k': {'type': 'integer', 'default': 5, 'description': 'Number of results (max 25).'}, 'kind': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional filter on the memory `kind`.'}, 'query': {'type': 'string', 'description': 'Natural-language search query.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
mnemos_store
PAID (0.01 USDC). Store a memory in your isolated bi-temporal namespace.
Append-only: `supersedes` marks a prior belief as no longer held WITHOUT
destroying it, so it stays queryable via mnemos_as_of. `valid_from`/`valid_to`
describe when the fact is true IN THE WORLD and may be backdated; the system's
own knowledge timestamps are server-stamped and cannot be forged.
Returns an x402 quote; requires header X-TENANT-KEY once settled.
输入模式
{'type': 'object', 'required': ['key', 'value'], 'properties': {'key': {'type': 'string', 'description': "Stable identifier for this fact (e.g. 'ACME.runway')."}, 'value': {'type': 'string', 'description': 'The memory content (max 6000 chars).'}, 'valid_to': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO8601 -- when it stopped being true (omit if still true).'}, 'supersedes': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'memory_id of the prior belief this replaces.'}, 'valid_from': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'ISO8601 -- when the fact became true in the world.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
notarize
PAID (0.10 USDC). Produce a tamper-evident notarization record (sha256 digest +
signed timestamp) for a piece of content. The quote preview already includes the
sha256 digest so you can verify integrity; the signed record follows payment.
输入模式
{'type': 'object', 'required': ['content'], 'properties': {'content': {'type': 'string', 'description': 'The content to notarize.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
research_brief
PAID (0.10 USDC). Structured synthesis brief on a topic, from local model
knowledge only. This tool does NO live web research and returns NO citations --
claims are not sourced. The delivered brief carries in-band caveats stating its
knowledge cutoff and limits. If you need cited, web-researched output, that is a
different product (research-brief-pro on the HTTP rail), not this one.
Returns an x402 quote + payment instructions; the brief is delivered after settlement.
输入模式
{'type': 'object', 'required': ['topic'], 'properties': {'depth': {'type': 'string', 'default': 'standard', 'description': "'quick' | 'standard' | 'deep'."}, 'topic': {'type': 'string', 'description': 'The research topic or question.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
summarize
PAID (0.03 USDC). Full-quality document summarization. Returns an x402 quote +
payment instructions; the summary is delivered after payment settles.
输入模式
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'The document to summarize.'}, 'max_words': {'type': 'integer', 'default': 200, 'description': 'Target maximum length of the summary in words.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
summarize_demo
FREE. A working demo of the paid `summarize` tool: returns a tiny deterministic
extractive summary (first + most-salient sentences, capped ~280 chars) so agents can
verify the connector end-to-end before buying. No payment, no auth required.
输入模式
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'The text to summarize (any length; only a short preview is returned).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
trust_check
PAID (0.05 USDC). Combined Trust Oracle probe: aggregate bazaar-index stats
(reachable/valid-402 counts, median latency) + a watchtower attestation for one
URL (reachable, returns_402, latency, score). Returns an x402 quote + payment
instructions; the combined result is delivered after payment settles.
输入模式
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The https URL to probe (watchtower).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
历史
近期工具变更
已添加
mnemos_as_of
2026年9月17日 12:38
已添加
mnemos_get_context
2026年9月17日 12:38
已添加
mnemos_search
2026年9月17日 12:38
已添加
mnemos_store
2026年9月17日 12:38
已添加
mnemos_provision
2026年9月17日 12:38
已添加
mnemos_saas_info
2026年9月17日 12:38
已添加
embed_batch
2026年9月17日 12:38
已添加
trust_check
2026年9月17日 12:38
已添加
notarize
2026年9月17日 12:38
已添加
research_brief
2026年9月17日 12:38
已添加
code_review
2026年9月17日 12:38
已添加
fact_verify
2026年9月17日 12:38
已添加
summarize
2026年9月17日 12:38
已添加
summarize_demo
2026年9月17日 12:38
已添加
agora_catalog
2026年9月17日 12:38
发现
类似的 MCP 服务器
Speedbot Autonomous Work Network
io.github.ulasarslan6262-ui/speedbot
Supports asynchronous collaboration, discovery, messaging, referrals, and optional USDC-based scenarios among AI agents.
Singularity Layer MCP
io.github.ivaavimusic/singularity
Provides marketplace discovery, agent endpoint and asset management, dataset and product purchases, payment flows, and ERC-8004 a…
agent4.io
io.agent4/agent4-tenant
Manages grounded business agents, knowledge bases, skills, connected MCP tools, public shares, and structured interactive storyli…
bookstore4agents
io.github.scott2121/bookstore4agents
Operates a marketplace for agents to discover, preview, purchase, download, annotate, publish, and monetize books and curated dom…
Agorean
com.agorean/agorean
Provides an agent marketplace for listing, discovering, purchasing, delivering, reviewing, and commissioning data, code, content,…
agentsouk
dev.agentsouk/agentsouk
Operates a marketplace where agents publish services, hire one another, manage jobs and disputes, and settle payments in USDC on …
xrpl-referee
io.github.eamwhite1/xrpl-referee
Supports XRPL-based agent hiring, escrow payments, job marketplaces, wallet trust scoring, sanctions and KYC checks, and AI-assis…
Swarm Tips — Earn, Spend, and Discover for AI Agents
io.github.corsur/swarm-tips
Provides AI-agent messaging, reputation, opportunity discovery, task marketplaces, wallet registration, and non-custodial crypto …