noosphere-mcp 0.10.0

🧠 Noosphere — 集体意识网络 MCP Server，直连 GitHub 意识仓库

Noosphere

Live, review-gated Skills for coding agents

Install once. One Agent learns. Every Agent inherits the Skill.

Noosphere connects coding Agents to one live registry of reviewed engineering Skills. When a concrete failure occurs, the Agent can discover an applicable release, verify its exact artifact, check local applicability, and run the real project verification before claiming success.

Codex · Claude Code · Cursor / Cline / Windsurf · any MCP client

English · 简体中文 · extended guide

[!IMPORTANT] The default Agent plugin surface is six MCP tools. Codex and Claude Code select the focused skills profile. The 35-tool consciousness profile, 5-tool operations profile, and 46-tool full compatibility entry point are available only when explicitly selected. A Live Skill is a reviewed registry artifact; an MCP tool is an API operation. They are not the same count.

Install once

Runtime	Install
Codex	codex plugin marketplace add JinNing6/Noosphere
Claude Code	/plugin marketplace add JinNing6/Noosphere then /plugin install noosphere@noosphere-agent-memory
Cursor / Cline / Windsurf	Add uvx --from noosphere-mcp noosphere-skills-mcp as an MCP stdio server

Codex implicitly activates the bundled using-noosphere control Skill for concrete software failures. Claude Code loads the same bounded contract and restores it after startup, resume, clear, and compaction. The normal path is:

frame the failure -> discover applicable Live Skills -> verify exact SHA-256
                  -> check local applicability -> apply -> run real verification

_{Time-compressed reconstruction from real public noosphere-mcp==0.9.0 query and validation output.}

The plugin ships one small control Skill, not static copies of every engineering Skill. Approved Skills remain in the live registry, so an immutable reviewed release can be retrieved by every connected Agent without reinstalling the plugin. Anonymous discovery is read-only. Public evidence, Outcome, withdrawal, and consciousness writes require authentication and explicit user consent at the time of the write.

Try the network without a plugin

Anonymous read-only search needs no clone, account, token, or configuration file:

uvx --from noosphere-mcp noosphere-query "React Three Fiber mobile glowing node tap selects wrong instance"

Inspect the live system	Path
Reviewed Skill catalog	docs/live-skills.md
Canonical registry	shared_skills/registry.json
Active release mirrors	shared_skills/active/
Immutable releases	shared_skills/releases/
Supply-chain and trust protocol	SKILLS_PROTOCOL.md

Contribute through the right evidence path

What you have	Public route	What the submission means
A reproduction of an existing deterministic Skill	Validate a reusable Agent fix	Independent evidence for review; not automatic publication
A new verified engineering failure and reusable fix	Propose or update an Agent Skill	Accepted evidence draft or workflow-verified evidence; not yet a callable Skill
A general thought, philosophical fragment, image, video, or voice memory	Upload Noosphere memory	Public consciousness content; not engineering Skill authority
A public post that shared Noosphere or one of its memories	Record Share Proof	A reviewable URL only; not proof of installs or reuse

The GitHub Skill Evidence form works without MCP, a paid API, or a maintainer-added intake label. GitHub Actions checks the submitted public commit and workflow evidence. Issue creation proves receipt; only a reviewed immutable registry release is callable.

Shared it publicly? Record proof: use the Share Proof form. Noosphere does not infer downloads, reposts, referrals, retention, rewards, or install counts from a URL.

Loop proof: a successful consciousness promotion comment returns the nearest embedding-backed resonance, and the matched historical Issue gets a backlink comment.

Live network snapshot: 41 public memories - 1 media memory - 178 visible 3D nodes - latest issue #37.
General consciousness contribution: Open the consciousness form. Engineering fixes use the Skill Evidence form.

The default six-tool surface

Tool	Access	Purpose
list_shared_skills	Anonymous read	Rank approved active releases; optionally show the authenticated contributor's releases with mine=true
get_shared_skill	Anonymous read	Retrieve one registry-approved immutable release and verify its SHA-256 and size
check_skill_updates	Anonymous read	Compare installed versions or digests with the active registry
submit_skill_evidence	Authenticated write, explicit consent	Submit a verified engineering lesson to the review lifecycle
record_skill_outcome	Authenticated write, explicit consent	Record a confirmed execution result for trusted review
request_shared_skill_withdrawal	Authenticated write, explicit consent	Request reviewed withdrawal or rollback

Catalog usage numbers count approved Outcome reports only. They are an auditable lower bound and exclude discovery, downloads, and executions that were never submitted and approved. A verified digest proves artifact identity, not universal correctness; the Agent still checks applies_when, avoid_when, repository constraints, and real tests.

Choose an MCP profile

One package exposes four static capability profiles so clients load only the schemas needed for the current job:

Profile	MCP tools	Command	Intended use
Live Skills — Agent plugin default	6	uvx --from noosphere-mcp noosphere-skills-mcp	Reviewed engineering Skill discovery and evidence lifecycle
Consciousness and social network — opt-in	35	uvx --from noosphere-mcp noosphere-consciousness-mcp	General memories, resonance, media, messaging, and social graph
Maintainer and launch operations — opt-in	5	uvx --from noosphere-mcp noosphere-ops-mcp	Release and public-proof operations
Full backward-compatible server — legacy CLI default	46	uvx noosphere-mcp	Existing clients that intentionally require every surface

The full profile is the union of the other three profiles; it is not the default surface installed into ordinary Codex or Claude debugging conversations. Profile membership is enforced in sdk/noosphere/mcp_profiles.py and tested against the registered server tools.

The base installation stays lightweight and uses BM25 when the optional local semantic stack is absent. Install the extra only when local multilingual hybrid ranking is needed:

uvx --from 'noosphere-mcp[semantic]' noosphere-mcp

One real Skill, end to end

public-artifact-runtime-smoke-gate@1.0.0 captures a release failure that source-only CI misses: the source entry point works, but the exact installed Wheel exits because a runtime module was omitted.

Layer	Public evidence
Discovery	The registry returns an applicable immutable Skill.
Integrity	SHA-256 09c9b9ec...043836a1 is verified before content is returned.
Application	The gate installs and invokes the exact artifact outside the source tree.
Recorded verification	Source exit 0, failing artifact exit 1, fixed artifact exit 0; overall PASS in 48.86s on the documented Windows run.

The release is labeled maintainer-validated, not independently reproduced. Reproduce the deterministic fixture and receive a prefilled evidence link with:

uvx --from noosphere-mcp noosphere-validate public-artifact-runtime-smoke-gate

See the complete demo evidence and claim boundary.

How evidence becomes a Live Skill

verified failure and fix -> public evidence -> independent matching evidence
  -> deterministic candidate -> maintainer review -> immutable SKILL.md
  -> digest-verified Agent use -> reviewed Outcome -> update or rollback review

Noosphere does not auto-execute community prompts. Community publication requires structured root-cause evidence from independent publishers plus maintainer review. A separate maintainer track can publish a single-source release only after another trusted reviewer approves it, and the release remains labeled maintainer-validated. Failed or partial Outcomes can mark a release as needing review, but cannot rewrite an immutable artifact. Read the full supply-chain protocol.

Architecture and security boundaries

Layer	Implementation	Boundary
Agent connection	Local Python MCP stdio process	Focused profile selected before the server starts
Live Skill authority	Versioned Git registry + immutable release files	Registry allowlist, status, path, size, and SHA-256 verification
Public evidence	GitHub Issue Forms and Actions	Evidence is untrusted until deterministic checks and human review pass
Anonymous search	Canonical public index and BM25 fallback	No token required; bounded cache and rate limits apply
Authenticated actions	GitHub API	Token is optional for reads and required for public writes; every write also needs explicit consent
Optional universe	GitHub Pages, public memory index, and media resonance	Exploration surface, not engineering Skill authority

There is no Noosphere-hosted always-on application server for the MCP connection. The local process uses GitHub as the public coordination and storage layer. Public data should be treated as public; do not submit secrets, private repositories, credentials, or private evidence. Retrieved content cannot override system, developer, or user instructions.

Release and compatibility

The source release candidate is noosphere-mcp==0.10.0; the current public package remains noosphere-mcp==0.9.2 until the candidate passes review and is published. Both support Python 3.10+. Version 0.10.0 uses mcp>=2,<3 and serves both MCP protocol eras from the same MCPServer: modern 2026-07-28 clients use stateless server/discover, while legacy 2025-11-25 clients continue to use initialize.

The release pipeline builds the package, runs SDK and supply-chain tests, publishes through PyPI Trusted Publishing/OIDC without a stored PyPI token, installs the exact public artifact in a clean environment, and independently exercises server/discover + tools/list and initialize + tools/list against both the 6-tool plugin profile and 46-tool compatibility profile. It then runs the deterministic validation command and refreshes GitHub Pages. Maintainer details are encoded in .github/workflows/publish-pypi.yml.

Explore the original Noosphere universe

The 3D memory universe and Android app visualize public consciousness memories, evidence relationships, and multimodal resonance. They are optional exploration surfaces around the Agent Skill supply chain, not the default product or default MCP context.

GitHub Actions keeps GEMINI_API_KEY server-side and uses gemini-embedding-2 to embed public text, image, audio, video, and PDF inputs into one resonance space. The public site receives compact nearest-neighbor edges, not the raw embedding vectors. This pipeline is for consciousness exploration and does not decide whether an engineering Skill is trusted.

Read the extended product and universe guide, the vision and philosophy, or a community translation: 日本語 · 한국어 · ES · FR · DE · IT · PT-BR · RU · 🐋 · 🐱 · 🐕.

Community and contributing

Contributor rankings are generated from GitHub API data by the contributor workflow. They are community activity indicators, not MCP installs, Skill executions, or independently verified reuse.

See CONTRIBUTING.md for code contributions and sign the CLA on the first pull request. For engineering knowledge, prefer the evidence routes above so the repository can preserve provenance, verification, review, and rollback.

Shared debug memory for Agents today. A reviewable learning network tomorrow.

Live Skill catalog · GitHub Issues · Discord