io.github.pouyahasanamreji/continuum

pnpm

Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.

68 114.2M/wk 7 tools GitHub npm

No known CVEs

No license

Maintained

Last commit 45d ago

Works with most clients

Transport: stdio, sse, http

7 tools · ~809 tok

Grade B · 0.4% of 200K ctx

Edit this pageView history

Productivity

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "io-github-pouyahasanamreji-continuum": {
      "args": [
        "-y",
        "pnpm"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-pouyahasanamreji-continuum)](https://mcppedia.org/s/io-github-pouyahasanamreji-continuum)

Read me

What io.github.pouyahasanamreji/continuum does

One MCP server. Tell any client to read the plot — it becomes the orchestrator. Dispatches fresh agents in isolated worktrees, shares lessons across every Claude Code / Codex / Cline chat on the project.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y 'pnpm' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

78/100across 5 weighted dimensions

How we score →

0255075100

−22

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

28 fixed

GHSA-qrv3-253h-g69chigh · fixedCVSS 8.2

pnpm: Path traversal in configDependencies env lockfile allows symlink creation outside node_modules/.pnpm-config

## Summary `pnpm` accepts package names from the env lockfile `configDependencies` section and uses those names directly when creating config dependency symlinks under `node_modules/.pnpm-config`. A malicious repository can commit a crafted `pnpm-lock.yaml` whose env-lockfile document contains a traversal-shaped config dependency name such as `../../PWNED_CFGDEP`. During `pnpm install`, pnpm installs the config dependency and creates a symlink at a path derived from that name. In local testin

Affected: >= 0Fixed in 10.34.4source →

GHSA-72r4-9c5j-mj57high · fixedCVSS 7.1

pnpm: `patch-remove` could delete project-selected files outside the patches directory

## Summary The `patch-remove` deletion-scope issue tracked as GHSA-72r4-9c5j-mj57 / CAND-PNPM-030 has been addressed in pnpm. A crafted patch entry could resolve outside the configured patches directory and cause `pnpm patch-remove` to delete an arbitrary reachable file. This patch validates the configured directory and every resolved target before unlinking anything, then deletes the final directory entry without following it. ## Security boundary - Traversal and absolute paths that resolve

Affected: >= 0Fixed in 10.34.4source →

GHSA-fr4h-3cph-29xvhigh · fixedCVSS 7.1

pnpm: Hoisted install imports lockfile alias outside node_modules

## Summary The hoisted dependency alias issue tracked as GHSA-fr4h-3cph-29xv / CAND-PNPM-059 has been addressed in both pnpm and pacquet. A crafted lockfile alias could be joined directly under a hoisted `node_modules` directory. Traversal aliases could escape that directory, while reserved aliases such as `.bin` or `.pnpm` could overwrite pnpm-owned layout. This patch validates package-name semantics and path containment before graph insertion or filesystem work. ## Security boundary - The

Affected: >= 0Fixed in 10.34.4source →

CVE-2026-55700high · fixedCVSS 7.1

pnpm: `stage download` writes outside its destination directory via manifest name/version traversal

## Summary The staged-tarball filename traversal reported as GHSA-v23m-ccfg-pq9h / CAND-PNPM-038 is fixed on `main` by [pnpm/pnpm#12303](https://github.com/pnpm/pnpm/pull/12303), merged as `65443f4bdf1f0db9c8c7dc58fee25252607e9234`. Before the fix, `pnpm stage download` derived a local filename from registry-controlled package name and version fields. A crafted manifest could escape the selected download directory and overwrite another reachable file. The merged fix validates both fields, deri

Affected: >= 11.3.0Fixed in 11.5.3source →

CVE-2026-55699medium · fixedCVSS 6.5

pnpm: Reserved bin name deletes PNPM_HOME during global remove

<details> <summary>Maintainer Action Plan</summary> ## Maintainer Action Plan This report is ready to review with the shared patch branch. Start with the PR and the expected fixed behavior, then use the detailed exploit narrative below only if you want to replay the original path. - Advisory: `CAND-PNPM-085` / `GHSA-4gxm-v5v7-fqc4` - Advisory URL: https://github.com/pnpm/pnpm/security/advisories/GHSA-4gxm-v5v7-fqc4 - Shared patch PR: https://github.com/pnpm/pnpm-ghsa-j2hc-m6cf-6jm8/pull/1 - S

Affected: >= 0Fixed in 10.34.2source →

Inventory

Tools (7)

Click any tool to inspect its schema.

~809 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.pouyahasanamreji/continuum safe to use?: io.github.pouyahasanamreji/continuum has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.pouyahasanamreji/continuum?: io.github.pouyahasanamreji/continuum supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.pouyahasanamreji/continuum do?: io.github.pouyahasanamreji/continuum provides 7 tools: knowledge_search, knowledge_get, knowledge_create, knowledge_list, registry_list and 2 more. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.pouyahasanamreji/continuum?: io.github.pouyahasanamreji/continuum is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.pouyahasanamreji/continuum actively maintained?: io.github.pouyahasanamreji/continuum is recently maintained — last commit was 45 days ago. It has 68 GitHub stars.

Similar servers

Others in productivity

View all →

Sequential Thinking MCP Server96

Dynamic problem-solving through sequential thought chains

87.8k 1

Memory MCP Server96

Persistent memory using a knowledge graph

87.8k 5

Superlocalmemory MCP Server94

Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.

188 6

com.monday/monday.com94

MCP server for monday.com integration.

412 4

MCP Security Weekly

Get CVE alerts and security updates for io.github.pouyahasanamreji/continuum and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

flowchart TD CC["Claude Code"] CX["Codex"] CL["Cline"] YOU["YOU"] subgraph CONTINUUM["CONTINUUM ORCHESTRATOR"] direction LR PLOT["PLOT.md protocol"] KNOW["KNOWLEDGE (vectorized)"] AGENTS["AGENTS registry"] PANEL["WEB PANEL (humans)"] end DB[("SQLite + sqlite-vec one file, your disk")] CC -- MCP --> CONTINUUM CX -- MCP --> CONTINUUM CL -- MCP --> CONTINUUM YOU -- HTTP --> CONTINUUM CONTINUUM --> DB

What you get


🧠 Vectorized memory	Every lesson your agents learn becomes a 768-dim embedding indexed in `sqlite-vec`. Recall is semantic, fuzzy, and instant — no exact-match games.
🔍 RAG-native search	`knowledge_search({q: "how do we handle webhook retries?"})` returns ranked metadata (slug + kind + agentSlug + timestamps); follow up with `knowledge_get({slug})` for the body. Metadata first keeps top-K context cheap; only fetch what's worth reading.
🗺️ Canonical workflow	Every project gets a PLOT.md seeded with a 4-phase dispatch protocol — Intake → Research → Verify → Handoff. Stop re-explaining your process.
🤖 Multi-agent registry	State machine + reserved-path tracking stops parallel agents from clobbering each other across git worktrees.
📚 Two-tier knowledge	`fundamental` lessons are binding rules loaded on every dispatch. `situational` lessons surface via semantic search when relevant.
🖥️ Human web panel	Astro + React UI to browse projects, agents, plot, and knowledge while AI clients drive everything via MCP.
🔌 Client-agnostic	Standard MCP / Streamable HTTP. Works with Claude Code, Codex, Cline, Cursor, or anything that speaks the protocol.
🔒 Local-first	One SQLite file. WAL mode. No cloud. Optional embedder is your call (O

🧠 Vectorized memory

Every lesson your agents learn becomes a 768-dim embedding indexed in sqlite-vec. Recall is semantic, fuzzy, and instant — no exact-match games.

🔍 RAG-native search

knowledge_search({q: "how do we handle webhook retries?"}) returns ranked metadata (slug + kind + agentSlug + timestamps); follow up with knowledge_get({slug}) for the body. Metadata first keeps top-K context cheap; only fetch what's worth reading.

🗺️ Canonical workflow

Every project gets a PLOT.md seeded with a 4-phase dispatch protocol — Intake → Research → Verify → Handoff. Stop re-explaining your process.

🤖 Multi-agent registry

State machine + reserved-path tracking stops parallel agents from clobbering each other across git worktrees.

📚 Two-tier knowledge

fundamental lessons are binding rules loaded on every dispatch. situational lessons surface via semantic search when relevant.

🖥️ Human web panel

Astro + React UI to browse projects, agents, plot, and knowledge while AI clients drive everything via MCP.

🔌 Client-agnostic

Standard MCP / Streamable HTTP. Works with Claude Code, Codex, Cline, Cursor, or anything that speaks the protocol.

🔒 Local-first

One SQLite file. WAL mode. No cloud. Optional embedder is your call (O

Frequently Asked Questions

Is io.github.pouyahasanamreji/continuum safe to use?

io.github.pouyahasanamreji/continuum has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.pouyahasanamreji/continuum?

io.github.pouyahasanamreji/continuum supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can io.github.pouyahasanamreji/continuum do?

io.github.pouyahasanamreji/continuum provides 7 tools: knowledge_search, knowledge_get, knowledge_create, knowledge_list, registry_list and 2 more. See the full tools list on the server page for descriptions and parameters.

What AI clients work with io.github.pouyahasanamreji/continuum?

io.github.pouyahasanamreji/continuum is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is io.github.pouyahasanamreji/continuum actively maintained?

io.github.pouyahasanamreji/continuum is recently maintained — last commit was 45 days ago. It has 68 GitHub stars.

What you get


🧠 Vectorized memory	Every lesson your agents learn becomes a 768-dim embedding indexed in `sqlite-vec`. Recall is semantic, fuzzy, and instant — no exact-match games.
🔍 RAG-native search	`knowledge_search({q: "how do we handle webhook retries?"})` returns ranked metadata (slug + kind + agentSlug + timestamps); follow up with `knowledge_get({slug})` for the body. Metadata first keeps top-K context cheap; only fetch what's worth reading.
🗺️ Canonical workflow	Every project gets a PLOT.md seeded with a 4-phase dispatch protocol — Intake → Research → Verify → Handoff. Stop re-explaining your process.
🤖 Multi-agent registry	State machine + reserved-path tracking stops parallel agents from clobbering each other across git worktrees.
📚 Two-tier knowledge	`fundamental` lessons are binding rules loaded on every dispatch. `situational` lessons surface via semantic search when relevant.
🖥️ Human web panel	Astro + React UI to browse projects, agents, plot, and knowledge while AI clients drive everything via MCP.
🔌 Client-agnostic	Standard MCP / Streamable HTTP. Works with Claude Code, Codex, Cline, Cursor, or anything that speaks the protocol.
🔒 Local-first	One SQLite file. WAL mode. No cloud. Optional embedder is your call (O

🧠 Vectorized memory

Every lesson your agents learn becomes a 768-dim embedding indexed in sqlite-vec. Recall is semantic, fuzzy, and instant — no exact-match games.

🔍 RAG-native search

🗺️ Canonical workflow

Every project gets a PLOT.md seeded with a 4-phase dispatch protocol — Intake → Research → Verify → Handoff. Stop re-explaining your process.

🤖 Multi-agent registry

State machine + reserved-path tracking stops parallel agents from clobbering each other across git worktrees.

📚 Two-tier knowledge

fundamental lessons are binding rules loaded on every dispatch. situational lessons surface via semantic search when relevant.

🖥️ Human web panel

Astro + React UI to browse projects, agents, plot, and knowledge while AI clients drive everything via MCP.

🔌 Client-agnostic

Standard MCP / Streamable HTTP. Works with Claude Code, Codex, Cline, Cursor, or anything that speaks the protocol.

🔒 Local-first

One SQLite file. WAL mode. No cloud. Optional embedder is your call (O