MCPFax Agent Continuity

Remember items you processed

seen_add

Idempotent

Record items you have already processed. FREE. Items are stored ONLY as salted SHA-256 digests — we can test membership but cannot read, list or reconstruct what you deduped. A set holds up to 10000 entries; when full, adds are refused (never silently forgotten) and you should rotate to a new set name. FREE — this tool never charges. Authenticate with Authorization: Bearer <agent_secret>, or pass agent_key as an argument if your host cannot set headers. Equivalent HTTP route: POST /v1/seen/add.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "set": "<set>",
      "items": "<items>"
    },
    "name": "seen_add"
  }
}

Input Schema

Name	Required	Description
`set`	Yes	Set name. Namespace-scoped, hashed before storage. Example: 'processed-ids'.
`items`	Yes	Up to 100 strings per call, each <=1024 chars. Example: '["id-1","id-2"]'.
`scope`	No	Optional unit of work, so resume_packet can report which sets you are deduping against. Example: 'permit-review-2026-08'.
`agent_key`	No	Your agent_secret, if your MCP host cannot set the Authorization header. Prefer the header.
`ttl_seconds`	No	Sliding set lifetime, refreshed on each add. Default 2592000 (30d), max 31536000. Example: '2592000'.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 4, 2026
- addedInput schema / properties / agent_key / examples
```
Added value: +[
+  "the agent_secret that register returned"
+]
```
Changed4 schema fields changedSep 4, 2026
- addedInput schema / properties / items / examples
```
Added value: +[
+  "[\"id-1\",\"id-2\"]"
+]
```
- addedInput schema / properties / scope / examples
```
Added value: +[
+  "permit-review-2026-08"
+]
```
- addedInput schema / properties / set / examples
```
Added value: +[
+  "processed-ids"
+]
```
- addedInput schema / properties / ttl_seconds / examples
```
Added value: +[
+  2592000
+]
```
First observedAug 14, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Beyond the annotations, the description discloses material behavior: privacy via salted SHA-256 digests, inability to read/list/reconstruct stored items, the 10,000-entry capacity, refusal-on-full instead of silent drops, auth requirements, and the no-charge guarantee. These are exactly the operational details an agent needs, and none contradict the annotations.

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

Conciseness4/5

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

The description is front-loaded with the core purpose and leads into privacy, capacity, then auth. The only real waste is repeating FREE twice, which is redundant but does not obscure meaning.

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

Completeness4/5

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

For a 5-param mutation tool without an output schema, it covers invocation, auth, capacity/refusal semantics, and storage guarantees. It does not describe return/response values or duplicate-item behavior, but idempotentHint covers idempotence and the documented capacity/auth details are the most important parts for correct invocation.

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

Parameters4/5

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

Schema coverage is 100%, but the description still adds param-relevant meaning: a set holds up to 10,000 entries and warrants rotation when full, and agent_key is positioned as an auth fallback. It does not cover scope or ttl_seconds in prose, but the schema already documents those clearly.

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 uses a specific verb ('Record') and resource ('items you have already processed'), and it clearly explains the deduplication/membership semantics with 'can test membership' and 'deduped'. This distinguishes seen_add from siblings like seen_check, which is the membership-query side.

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

Usage Guidelines3/5

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

The description conveys when to record processed items and gives conditional guidance ('when full... rotate to a new set name'), but it does not explicitly say when not to use this tool or direct the agent to a sibling like seen_check for membership tests. Usage context is inferable rather than stated as a decision rule.

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

All MCPFax Agent Continuity tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?