Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Fireweed

PYPI · FIREWEED-MCP · SCANNED SEP 21

Agent memory where every fact carries a receipt, and deletion is provable.

Available components

+18 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency32
Schema Quality & AI Usability79
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 712 tokens (~71/item across 10 items; 10 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 69% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "forget" implies "erase" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the Fireweed MCP server?

Fireweed runs locally as a PyPI package, launched with uvx fireweed-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · fireweed-mcp

# add to Claude Code
claude mcp add starksood-fireweed-mcp -- uvx fireweed-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "starksood-fireweed-mcp": {
      "command": "uvx",
      "args": [
        "fireweed-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "starksood-fireweed-mcp": {
      "command": "uvx",
      "args": [
        "fireweed-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add starksood-fireweed-mcp -- uvx fireweed-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "starksood-fireweed-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "fireweed-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add starksood-fireweed-mcp --command uvx --arg fireweed-mcp
# ~/.hermes/config.yaml
mcp_servers:
  starksood-fireweed-mcp:
    command: "uvx"
    args: ["fireweed-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "starksood-fireweed-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "fireweed-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add starksood-fireweed-mcp -t stdio -c uvx -a fireweed-mcp
// mcp.json
{
  "mcpServers": {
    "starksood-fireweed-mcp": {
      "command": "uvx",
      "args": [
        "fireweed-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed pypi/fireweed-mcp@0.5.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 10 exposed · ~712 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
add_source ~121

Register a source document so claims remembered against it bind to verifiable byte ranges.

NameTypeReqDescription
originstringwhere these bytes came from (path, URL, endpoint). RECORDED BUT NOT VERIFIED.
origin_kindstringthe kind of origin. Recorded but not verified.
source_idstringyes
supplied_bystringwho handed these bytes over. Recorded but not verified.
textstringyes
validated_bystringwhat checked these bytes before ingest, if anything. Recorded but not verified.

No output schema declared.

No examples provided.

export_memory ~44

Export the whole substrate as a portable open-format blob. Readable without this server, without any model, with a stdlib-only reference reader.

NameTypeReqDescription
pathstring

No output schema declared.

No examples provided.

forget ~61

Erase everything about a subject and issue a SIGNED CERTIFICATE: exact closure, a probe battery that must all abstain, and bystanders left intact. This is the artifact for a 'delete me and prove it' request.

NameTypeReqDescription
subjectstringyes

No output schema declared.

No examples provided.

memory_stats ~20

Substrate size, entities, sources held, and mode.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

recall ~59

Search memory. Returns grounded claims with the byte ranges they came from. If the substrate cannot answer, it ABSTAINS and says which term it could not ground — treat that as a real answer, not an empty result.

NameTypeReqDescription
querystringyes

No output schema declared.

No examples provided.

remember ~143

Commit a fact to memory. The claim is admitted ONLY if the evidence you cite supports it — you are the proposer, a deterministic gate decides. Refusals are typed and explain what to fix. Evidence must be text you are quoting verbatim, not a paraphrase.

NameTypeReqDescription
claimstringyesthe fact to remember
evidencestringyesverbatim text supporting it
source_idstringsource this came from (default: agent)
source_textstringthe full document this evidence was quoted from. Pass it and the claim binds to a verifiable BYTE RANGE in it — the receipt. Optional, but this is the point.

No output schema declared.

No examples provided.

review_quarantine ~62

List claims the firewall held for review rather than storing. These were NOT written to memory; a QUARANTINE verdict means the claim could not be classified confidently, not that it was rejected.

NameTypeReqDescription
limitintegermost recent N (default 20)

No output schema declared.

No examples provided.

review_reads ~75

What has been asked of this substrate and what it answered. Off unless FIREWEED_MCP_READ_AUDIT=1; query text is recorded only if FIREWEED_MCP_READ_AUDIT_TEXT=1 as well, otherwise queries appear as salted fingerprints.

NameTypeReqDescription
limitintegerhow many recent reads to show

No output schema declared.

No examples provided.

trace_evidence ~87

Audit BACKWARDS from a stored memory to the arrival of the evidence it rests on: the byte range it binds, whether those bytes still match, whether the document's arrival is in the append-only ledger, and whether the chain verifies. States plainly which fields are attested and which are caller-declared.

NameTypeReqDescription
claimstringyesany distinctive substring of the stored claim to trace

No output schema declared.

No examples provided.

verify_receipts ~40

Re-hash every held source and re-slice every receipt. Tamper-evident: change one byte of a source and its receipts stop verifying.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the Fireweed MCP server?

Fireweed is an MCP server listed in the public MCP registry as io.github.Starksood/fireweed-mcp. Agent memory where every fact carries a receipt, and deletion is provable. This page covers its PyPI package (fireweed-mcp).

Is the Fireweed MCP server safe to use?

Fireweed scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Fireweed MCP server expose?

Fireweed exposes 10 tools: remember, add_source, review_reads, trace_evidence, recall, and 5 more. Their descriptions and schemas cost roughly 712 tokens of context every time the server is loaded.

Is the Fireweed MCP server still maintained?

Fireweed is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.