Symbola MCP server
io.github.spikinglabs/symbolaspikinglabsstreamable-httpv0.1.0Scanned
Search software packs on symbola.sh, read their decisions, and get steps to build them.
5 tools: 5 only read.
- Reads private data · 2
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Symbola MCP server can do
The Symbola MCP server is published by the GitHub account spikinglabs. It has 5 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
2 tools read private data (get_pack and read_pack_file).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 9, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
5 tools
Only reads 5Show 5 read-only tools
get_build_stepsHow to build a pack: the steps a coding agent with a shell follows (install the symbola CLI, pull the pack, build each component and run its checks), and a one-line request the use…No findings
Why it is in this group
- The name "get_build_steps" says "get": a word for reading.
Description, as the server wrote it How to build a pack: the steps a coding agent with a shell follows (install the symbola CLI, pull the pack, build each component and run its checks), and a one-line request the user can paste into Claude Code or another coding agent.
Annotations the server declares
- title: Get build steps
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_packOverview of one pack: what it builds, its version, how many decisions it holds, its components, its page and download link, and the files it holds.Reads private dataNo findings
Why it is in this group
- The name "get_pack" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
Description, as the server wrote it Overview of one pack: what it builds, its version, how many decisions it holds, its components, its page and download link, and the files it holds.
Annotations the server declares
- title: Get a pack
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
read_decisionsThe decisions a pack makes: each one a rule a builder could get wrong, with its status (decided, default or open).No findings
Why it is in this group
- The name "read_decisions" says "read": a word for reading.
Description, as the server wrote it The decisions a pack makes: each one a rule a builder could get wrong, with its status (decided, default or open). Narrow them to one component or to decisions mentioning some words.
Annotations the server declares
- title: Read decisions
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
read_pack_fileRead one file of a pack, e.g.Reads private dataNo findings
Why it is in this group
- The name "read_pack_file" says "read": a word for reading.
What it can reach
- private-dataThe name "read_pack_file" says "read" and "file": it reads files.
- private-dataThe description's first sentence says "read" and "file": it reads files.
Description, as the server wrote it Read one file of a pack, e.g. PRODUCT.md (the whole product), AGENTS.md (how to build it), BRIEF.md, obligations.toml, an assumption, or a component's symbolon.toml or examples.jsonl. "pack.md" is the whole pack as one Markdown page.
Annotations the server declares
- title: Read a pack file
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_packsSearch the Symbola registry for packs: software a coding agent can build from its decisions.No findings
Why it is in this group
- The name "search_packs" says "search": a word for reading.
Description, as the server wrote it Search the Symbola registry for packs: software a coding agent can build from its decisions. Matches words against each pack's name, summary, id and category. With no query, lists every pack.
Annotations the server declares
- title: Search packs
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 19, 2026, 17:24 UTC, unchanged since Oct 28, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http symbola https://symbola.sh/mcpclaude mcp add --transport http symbola https://symbola.sh/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__symbola__search_packs",
"mcp__symbola__get_pack",
"mcp__symbola__read_decisions",
"mcp__symbola__read_pack_file",
"mcp__symbola__get_build_steps"
],
"ask": [],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as symbola. Review it before you use it.
Capability tags behind 2 rules
- mcp__symbola__get_pack private-data
- mcp__symbola__read_pack_file private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.spikinglabs/symbola/verify?hash=903c4f64a047b500ccfee70d437d59258de6b891e856fafa327cb54cf3b4ec6d" | jq -e '.changed == false'Pinned hash 903c4f64a047, from Nov 9, 2026, 22:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.spikinglabs/symbola/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.spikinglabs/symbola)Source: MCP Registry. Synced Oct 28, 2026, 07:17 UTC.
Symbola MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Symbola MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Symbola MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Symbola MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Symbola MCP server have?
- 5 tools: 5 read. search_packs, get_pack, read_decisions, read_pack_file and get_build_steps.
Does the Symbola MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Symbola MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Symbola MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.