recon
v2.27.1by blisspixel · author: pueo-labs
Public-metadata domain intelligence through the recon MCP server and portable skills.
Package we checked
The manifest we fetched is agents/agent-plugin/plugin.json in blisspixel/recon. The plugin root is the directory that holds that file. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 2 skills (recon-fingerprint-triage, recon) and 1 MCP server (recon). Stored mcp.json transports: recon stdio.
What recon does, in the publisher's words
Schema-pinned portable packaging candidate for recon-tool 2.19.0. It contains the complete MCP surface and the two existing recon skills in the fixed Agent Plugins v1.0.0 locations.
This directory has passed offline validation against the vendored canonical Agent Plugins v1.0.0 schemas. Version 1.0.0 is Published. Offline validation is not an unqualified compatibility or conformance claim; promotion remains blocked on the frozen Visual Studio Code, Cursor, and Kiro representative-client evaluation.
Prerequisites:
- Python 3.11 or newer;
- recon-tool installed so the client can resolve the recon executable;
- client-controlled approval for any networked lookup.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 2
- MCP servers
- 1
- Stars
- 0
- License
- Apache-2.0
Links
Skills · 2
- recon-fingerprint-triage
- Triage recon fingerprint candidates across the bounded DNS catalog surface. Reads private single-domain discovery output, aggregate catalog baselines, or candidate queues, then classifies candidates as pending, promoted, rejected, or deferred under the v2.14 catalog-quality gates. Use when the user…
- recon
- Public-metadata domain intelligence: Microsoft 365 / Google Workspace tenant identification, email security configuration (DMARC, DKIM, SPF, MTA-STS, BIMI), SaaS fingerprinting from DNS, certificate-transparency findings, related-domain discovery. Use when a domain name appears alongside phrases l…
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- reconstdio
- recon mcp
- env vars: RECON_CONFIG_DIR
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Security & Compliance. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
recon · dns · domain-intelligence · mcp · agent-skills
Related by publisher and keywords
Bounded research and persistent expert discovery through an Agent Skill and a local read-only MCP capability profile.
A mathematical world where digital minds and humans can explore, predict, create, and share wonder.
Play deterministic Vibe Snake matches through a local.NET 10 MCP host and produce verified replays.
Report-only Meshtastic intent planning, spectrum reduction, and the MeshToad plus T-Deck bench. Does not write to a radio unless a skill says so and a human runs it.
Read, verify, and curate a receipt-backed Distill research corpus, including bounded active-session worker handoffs.
Capture local AI candidates, interpret measured evidence, and expose read-only role summaries through MCP.
[](https://agentpluginsdirectory.com/plugins/recon)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.