Skip to main content
Glama

till_key_exposure

WHAT KEY MATERIAL IS ON THIS DISK, AND WHAT STILL HOLDS AN OLD COPY OF IT? The companion to till_seed_exposure, and it exists because a real theft happened without the phrase ever being written down: the key was exfiltrated. The trap is that a secp256k1 private key is 64 hex characters and so is every SHA-256 hash, git object id and transaction hash in a saved response, so the value SHAPE carries almost no information. Two things do: STRUCTURE (a Web3 Secret Storage keystore has version 3 and a crypto member with ciphertext, kdf and mac — nothing else looks like that, and finding one is not an exposure but an encrypted wallet whose strength is its password) and THE LABEL (cleartext keys are named by what needs them, so PRIVATE_KEY matches and PRIVATE_KEY_HASH is rejected as a digest). RETAINED COPIES are what people miss: ROTATING A SECRET DOES NOT REMOVE IT FROM THE DISK, because editor history, session caches and backup folders keep snapshots of what the file used to say — on the machine this was built for, one .env holding three named keys had eighteen previous versions still readable, and the folder had been copied into a keep-across-the-reformat backup. Also reports browser wallet vaults by PRESENCE only, nothing opened or parsed, because that is how a key leaves a machine when it was never in a text file. Never outputs key material, not even a prefix: four bytes narrow a brute force. Never decrypts, never derives an address.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathsNodirectories to scan; defaults to Documents, Desktop and Downloads

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully discloses behaviors: scanning directories, detecting keys by structure/label, finding retained copies in editor history and backups, reporting browser vaults by presence only, and never outputting key material or decrypting. It also warns about the trap of SHA-256 hashes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is verbose and includes a narrative about a real theft, making it longer than necessary. While the first sentence is effective, the rest contains excessive detail that could be condensed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (detecting keys, retained copies, browser vaults), the description covers all essential aspects: detection logic, common pitfalls, and what the tool does not do. It is comprehensive despite lacking an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one optional parameter 'paths' with a description that matches the tool's description (defaults to Documents, Desktop, Downloads). Schema coverage is 100%, so the description adds no new parameter semantics beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: scanning disks for key material (private keys) and identifying retained copies. It distinguishes itself from its companion tool 'till_seed_exposure' and explains detection methods (structure and label).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context for when to use this tool (investigating key exposure) and contrasts it with till_seed_exposure. It also notes what the tool does not do (never outputs key material, never decrypts), but lacks explicit exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0
Disambiguation3/5

Many tools have distinct, well-named purposes (vet_agent vs vet_merchant), but there is notable overlap between till_trust and till_vet_merchant (both provide trust verdicts), and till_launch_funder vs till_funder_history are closely related. The descriptions are detailed enough to differentiate, but an agent could still misselect between a few pairs.

Naming Consistency3/5

All tools share the till_ prefix, but the pattern is mixed: some use verb_noun (check_invoice, create_charge, watch_wallet) while others are noun phrases (key_exposure, open_approvals, rug_powers) or bare nouns (floor, trust, roll). This is readable but not predictable, so an agent cannot reliably guess a tool name from a verb.

Tool Count2/5

At 29 tools, this server exceeds the 25+ threshold that signals an overgrown toolkit. Even with a broad domain, many tools are one-off niche scanners (till_b20_authentic, till_floor, till_meter) that inflate the surface and could be consolidated or externalized.

Completeness4/5

The toolkit covers the payment lifecycle comprehensively: create charges/invoices, check payments, verify delivery, generate receipts, rolls, and accounting exports. It also spans identity, trust, security scanning, and theft tracing. Minor gaps exist (no update/cancel for charges, no token-general vetting), but the non-custodial, read-only design makes these acceptable.