Waggle MCP
Persistent graph-backed conversational memory for AI agents.
Connector by Abhigyan-Shekhar · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Waggle MCP?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/abhigyan-shekhar-waggle-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.
- Tools
- 2 read · 3 write · 0 delete
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Tools by what they do 5
Read from the source code; the running server may list different tools.
Read 2 · Look things up without changing anything.
get_project_briefrecall_memory
Write 3 · Create, change, send or run things.
apply_approved_memory_changeload_abhi_for_sessionpropose_memory_change
Secrets and settings it asks for
Other settings (environment variables or headers).
WAGGLE_BACKENDWAGGLE_DB_PATHWAGGLE_DEFAULT_TENANT_IDWAGGLE_MODELWAGGLE_TRANSPORT
Network hosts it talks to 20
accounts.google.com· found in codeacme-staging-v02.api.letsencrypt.org· found in codeacme-v02.api.letsencrypt.org· found in codeai-gateway.vercel.sh· found in codeapi.github.com· found in codeapi.groq.com· found in codeapi.openai.com· found in codeapi.pinference.ai· found in codeapi.portkey.ai· found in codedaytona.io· found in codedocs.primeintellect.ai· found in codee2b.dev· found in codegithub.com· found in codeglama.ai· found in codegoogleapis.com· found in codehost.docker.internal· found in codeoauth2.googleapis.com· found in codeopenrouter.ai· found in codewaggle-webmcp.onrender.com· found in codewagglemcp.vercel.app· found in code
Files it touches
%APPDATA%\\Claude\\claude_desktop_config.json~/.config/claude/claude_desktop_config.json/dev/null/private/tmp/oolong-pairs-paper-eval.db/tmp/broker.py/tmp/rlm_exec_script.py/tmp/rlm_state.dill/tmp/run_script.py/Users/abhigyanshekhar/.waggle/memory.db%APPDATA%%APPDATA%\\Antigravity\\User\\mcp.json%APPDATA%\\Cursor\\User\\mcp.json%USERPROFILE%%USERPROFILE%\\.gemini\\antigravity\\mcp_config.json- Your home directory (~)
~/.codex/config.toml~/.cursor/mcp.json~/.gemini/antigravity/mcp_config.json~/.waggle/exports~/.waggle/google-client-secret.json~/.waggle/keys~/.waggle/merge-strategies.yaml~/.waggle/waggle.db
Tools (5)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
apply_approved_memory_changeUse 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_briefread-onlyUse 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_sessionUse 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's server, and disappears when this browser tab/session closes or the user resets it.
propose_memory_changeUse 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_memoryread-onlyUse 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.
Signals
- Stars
- 44
- Forks
- 138
- Open issues
- 171
- Weekly downloads
- 16
- Last commit
- Oct 8, 2026 (28 days ago)
- Last release
- Aug 10, 2026 (2 months ago)
- Last package publish
- May 7, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.Abhigyan-Shekhar/Waggle-mcp- Version
- 0.1.8
- Auth
- No auth
- Packages
- pypi waggle-mcp
- License
- Apache-2.0
- Repository
- github.com/Abhigyan-Shekhar/Waggle-mcp
- First seen
- Oct 24, 2026
- Last checked
- Nov 1, 2026
More from Abhigyan-Shekhar
- 0.617score
install-waggle
Abhigyan-Shekhar
Install the official Waggle plugin locally for Codex from the latest stable Abhigyan-Shekhar/Waggle-mcp GitHub Release.
SkillBFreshness: B★ 44Claude Code +9 - 0.614score
waggle-memory
Abhigyan-Shekhar
Use Waggle automatically as portable, local project memory during meaningful coding work; retrieve prior decisions and constraints, then store only durable…
SkillBFreshness: B★ 44Claude Code +9 - 0.609score
waggle-checkpoint
Abhigyan-Shekhar
Checkpoint durable decisions, fixes, constraints, results, and open next steps from the current Codex task into scoped Waggle project memory.
SkillBFreshness: B★ 44Claude Code +9 - 0.606score
waggle-prime
Abhigyan-Shekhar
Prime a Codex task with the most relevant Waggle project history before starting or resuming substantial work.
SkillBFreshness: B★ 44Claude Code +9 - 0.606score
waggle-recall
Abhigyan-Shekhar
Recall project-scoped Waggle history about a topic, component, decision, bug, experiment, or implementation attempt.
SkillBFreshness: B★ 44Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Waggle MCP running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Waggle MCP. Agent Mart. https://agentmart.dev/connectors/abhigyan-shekhar-waggle-mcp (last updated 2026-11-01)