Fireweed
PYPI · FIREWEED-MCP
Agent memory where every fact carries a receipt, and deletion is provable.
Available components
Last scanned (19 hours ago)
Scores higher than 84% of PyPI servers
Category Memory and Knowledge
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 build step with no custom scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency58
- Repository presence not verified: we could not reach the forge to check. This is a gap on our side, not a finding about the repository. View diagnostics → Unverified
- Cryptographically verified build provenance (signed, bound to Starksood/fireweed-mcp). View diagnostics → Pass
- License check failed: the license (LicenseRef-FSL-1.1-ALv2) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 68 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Provenance in Provenance & TransparencyRepository presence not verified: we could not reach the forge to check. This is a gap on our side, not a finding about the repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 5 Nov 26 −6
- Provenance: pass → unverified ▼ security
- 2 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 1 Nov 26 +1
- Stability: 0.97 → pass security
- 31 Oct 26 −16
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.97 functional
- 29 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 28 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 27 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 26 Oct 26 −15
- Malware scan: pass → unverified ▼ security
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 5 Nov 2026 · Analysed pypi/fireweed-mcp@0.5.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | Starksood/fireweed-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Starksood/fireweed-mcp/.github/workflows/publish.yml@refs/tags/v0.5.0 |
| Rekor log index | 2626684321 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:62856ec3bae9076f7d17ae97619274f870505265fea97726db7ac8d49a81f4f5 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | 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 →
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 →
add_source ~121
Register a source document so claims remembered against it bind to verifiable byte ranges.
| Name | Type | Req | Description |
|---|---|---|---|
| origin | string | – | where these bytes came from (path, URL, endpoint). RECORDED BUT NOT VERIFIED. |
| origin_kind | string | – | the kind of origin. Recorded but not verified. |
| source_id | string | yes | – |
| supplied_by | string | – | who handed these bytes over. Recorded but not verified. |
| text | string | yes | – |
| validated_by | string | – | what 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.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | – | – |
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.
| Name | Type | Req | Description |
|---|---|---|---|
| subject | string | yes | – |
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.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
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.
| Name | Type | Req | Description |
|---|---|---|---|
| claim | string | yes | the fact to remember |
| evidence | string | yes | verbatim text supporting it |
| source_id | string | – | source this came from (default: agent) |
| source_text | string | – | the 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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | most 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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | how 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.
| Name | Type | Req | Description |
|---|---|---|---|
| claim | string | yes | any 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.
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
claude mcp add starksood-fireweed-mcp -- uvx fireweed-mcp
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 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. 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 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Fireweed MCP server under?
Fireweed declares the LicenseRef-FSL-1.1-ALv2 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.
What did VerifyMCP test on the Fireweed MCP server?
VerifyMCP ran 15 checks on Fireweed, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Fireweed: Provenance. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.