fireweed-mcp
fireweed-mcp
代理记忆,每条事实都附有收据。
remember(claim = "Priya joined Acme in 2019 under duress.",
evidence = "Priya Raman joined Acme in 2019 as a logistics analyst.")
REFUSED (asserts_more_than_evidence) — the claim adds something the evidence does not say.
claim : Priya joined Acme in 2019 under duress.
evidence: Priya Raman joined Acme in 2019 as a logistics analyst.recall("Priya's salary")
ABSTAINED (unknown_predicate) — no claims ground "salary"; 1 claim about Priya Raman exists
This is a refusal, not an empty result.forget("Priya")
ERASED Priya Raman — certificate issued
signature : hmac-sha256:f4d0768ef3b0fec624afec12f25bfd91…
nodes in closure : 1
every probe abstains : True
bystanders surviving : 1最后那个就是 "从你的代理记忆中删除我——并证明它" 背后的产物。
安装
uvx fireweed-mcp # try it
pip install fireweed-mcp # keep itclaude mcp add fireweed -- uvx fireweed-mcp无依赖。无 API 密钥。无模型——此服务器中没有任何东西调用 LLM。
Related MCP server: Nahuali
它的功能
工具 | |
| 仅在你引用的证据支持该主张时接纳它。拒绝会给出类型,并说明需要修正什么。 |
| 用来源的字节范围来支撑主张;若无法支撑则弃权,并指出无法支撑的术语 |
| 重新哈希每个来源,重新切片每个范围——防篡改 |
| 具有精确闭包和签名证书的擦除;旁观者不受影响 |
| 将整个底层数据导出为可移植的开放格式 blob |
为什么拒绝才是重点
大多数记忆服务器存储模型所说的内容,并返回最接近的内容。这个服务器进行裁决。
规则是 模型提议,确定性代码决定。 跨越 RPC 边界,这就不再是一句口号:你的代理是提议者,它无法通过说服绕过门禁,因为门禁不是提示词。传入一个主张和你引用的文本;纯函数会检查证据是否提及主题、是否保持关系、是否虚构数字,以及是否断言了文本片段未说的内容。存活下来的内容会与来源的字节范围一起存储。
之后任何人都可以检查它——包括既不信任你的代理也不信任此服务器的人。这就是整个产品的意义。
它不做什么
事先说明,因为这个项目上一个头条数字最终被证明是在测量虚无(参见 撤回声明,该声明附带一个证明此事的脚本):
它不会从自由文本中提取记忆。 你提供主张和证据。 自动提取需要感知模型;此服务器刻意没有。
它不会让 LLM 变得诚实。 它管理的是进入记录的内容以及关于记录可证明的内容。你的模型仍然可以在自己的表述中随意说任何话。
对话式回忆较弱,且可测量。 在 1,200 条对抗性语料上,检索门禁仅在 40% 的问题上弃权,而这些问题确实没有答案——它检查的是问题的主题是否被支撑,而不是所问的值是否存在。写入路径、收据和擦除不受影响,且是值得依赖的部分。
你的数据
~/.fireweed/mcp/(可用 FIREWEED_MCP_STORE 更改)。底层数据是开放格式——参见 open_format/SPEC.md——而 open_format/reference_reader.py 仅用标准库即可读取。你的记忆比此服务器、此引擎和任何模型都长寿。一个测试断言了这种往返。
可选:pip install "fireweed-mcp[semantic]" 可在 recall 中启用释义匹配。没有它,门禁会拒绝更多——这是安全方向——而 memory_stats 会告诉你当前处于哪种模式。
许可证
FSL-1.1-ALv2 — 源代码可用。除构建竞争产品外,免费用于一切;将于 2028-01-01 转换为 Apache 2.0。全文见 LICENSE.md。
想在商业产品或竞争服务中使用 Fireweed?→ sanyamsood2@gmail.com
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceVerified memory for AI agents — agents propose memories that are quarantined until verified against evidence, and recall() returns only trusted, fresh, and in-scope facts, preventing poisoned or hallucinated data from spreading.141MIT
- FlicenseNot gradedqualityAmaintenanceLocal-first memory for AI agents with evidence-backed recall, deterministic trust verdicts, self-inspection, and a tamper-evident audit history.3

Lians Agent Memoryofficial
AlicenseAqualityAmaintenanceLocal-first bitemporal memory for AI agents with deterministic supersession, point-in-time recall, erasure proofs, and tamper-evident audit history.298Apache 2.0- AlicenseNot gradedqualityBmaintenanceA trusted memory and predictive analysis MCP server for AI agents, enabling evidence-based memory management, pattern analysis, and decision support with full audit trails.MIT
Related MCP Connectors
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Tamper-evident audit log service for agent-to-agent transactions
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Starksood/fireweed-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server