WaggleBLOCK
MCP server for external memory layer for AI agents + more . Download from pypi , and get started
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Project memory for humans and AI agents. Keep decisions, context, and the reasons behind them across conversations.
Install Waggle · Try the browser workspace · Documentation
Keep the context, not just the conversation
Waggle is an open-source, local-first memory layer for AI agents. It stores project knowledge as a graph: what you decided, why it matters, what it depends on, and what has changed. Your next conversation can pick up from that context instead of starting over.
Use Waggle with your MCP client, inspect and edit memory in Graph Studio, or bring a portable memory graph into the browser workspace.
- Continue across sessions. Recall project decisions, requirements, preferences,
and open questions without repeatedly pasting context.
- Understand the reasoning. Explore relationships, supporting evidence,
contradictions, and the history behind a decision.
- Keep control of corrections. In the WebMCP workspace, agents propose changes;
humans approve the exact content before it becomes authoritative.
- Take memory with you. Export and import
.abhifiles across supported
workflows without tying your graph to one client.
- Start locally. The default SQLite store li
832dc0729a36OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add waggle-mcp -- None waggle-mcp==0.1.25
Exposed tools (5)
4 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
apply_approved_memory_change | write | Use this Waggle Site tool when the user explicitly asks to apply a proposal that a human already approved in Waggle. It accepts only the approved proposal ID and cannot alter the approved content or bypass human review. |
get_project_brief | read | Use this read-only Waggle Site tool when the user asks to catch up on, brief, summarize, or get the current state of the project open in this workspace. It returns authoritative project memory; do not substitute chat history. |
load_abhi_for_session | read | Use this Waggle Site tool when the user attaches a .abhi file and asks to load or discuss it for this browser session. Pass the attached file bytes as base64. The file is parsed in the page, kept only in sessionStorage, never uploaded to Waggle |
propose_memory_change | read | Use this Waggle Site tool when the user asks to correct, replace, or propose a better version of an existing authoritative memory without changing it directly. It creates a human-review proposal and does not modify the authoritative memory. |
recall_memory | read | Use this read-only Waggle Site tool when the user asks what was decided, remembered, constrained, or is currently authoritative about a topic in the project open in this workspace. Superseded and expired memories are excluded. |
Trust audit
BLOCKgrade F · trust 38/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (10 observation(s))
- Network
- declared (9 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
b64decode( ... exec(
b64decode( ... exec(
b64decode( ... exec(
b64decode( ... exec(
b64decode( ... exec(
print(" OOLONG-PAIRS PAPER-ALIGNED EVAL (Groq + Waggle)")exec(code, combined, combined)
"id_ecdsa",
"id_ed25519",
"id_rsa",
install-waggle-openai-skill.zip
loaded[name] = importlib.import_module(f"waggle.server.{name}")baseUrl: `http://127.0.0.1:${this.port}`,return { baseUrl: `http://127.0.0.1:${this.port}`, port: this.port };const runtime = { baseUrl: `http://127.0.0.1:${this.port}`, port: this.port };const request = http.get(`http://127.0.0.1:${port}/health/live`, (response) => {SECRET = "ghp_fixtureSecretMustNeverLeak123456789"
token = "github_pat_11ABCDEFG0123456789_abcdefghijklmnopqrstuvwxyz"
SECRET = "ghp_fixtureSecretMustNeverLeak123456789"
token = "github_pat_11ABCDEFG0123456789_abcdefghijklmnopqrstuvwxyz"
demo.abhi
branched.abhi
empty.abhi
linear-history.abhi
.codexignore
Gates applied: critical_finding, no_behavioural_pass.
832dc0729a36full audit observations/trust-audit/mcp-server/abhigyan-shekhar__waggle.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 832dc0729a36 | BLOCK | F | 38 | first audit |
Questions
What is the Waggle MCP server?
MCP server for external memory layer for AI agents + more . Download from pypi , and get started
What tools does Waggle expose?
5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Waggle safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (38/100) and found 10 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Waggle need?
It reads AI_GATEWAY_API_KEY, AZURE_OPENAI_API_KEY, DAYTONA_API_KEY, GEMINI_API_KEY, GITHUB_TOKEN, GROQ_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY, PRIME_API_KEY, WAGGLE_API_KEY_ENVIRONMENT and WAGGLE_NEO4J_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Waggle run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as waggle-memory at 0.1.25.
How current is this page?
The grade is for one exact copy of the source (832dc0729a36), read on 2026-10-08. The repository is watched and re-audited when it changes.